Compare commits

...

320 Commits

Author SHA1 Message Date
Jason Wen 6fd4278e02 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-08-25 02:03:09 -04:00
Jason Wen 25c25047b8 models: persist model selection per catalog across chestnut state changes (#1960) 2026-08-25 01:12:12 -04:00
Jason Wen cefe5737b9 models: fix current model not updating on chestnut status (#1959)
* models: preserve user model selection across reboots and power cycles

* no

* again

* idk

* over
2026-08-25 00:41:31 -04:00
Jason Wen 760c19d3f9 ui/models: handle missing files during cache size calculation (#1958) 2026-08-24 23:31:52 -04:00
James Vecellio-Grant 45814e3313 modeld_v2: spatial features (#1934)
* modeld_v2: spatial features

* Update fetcher.py

* dont reshape non 4 dim arrays

* realize for non compiled

* Update compile_modeld.py

* god dammit it was realize()

* it was fucking frozen tinygrad. just need to recompile

* bump

* ci: add is_big flag to metadata.json to support backward compat

* Update model_generator.py

* Update sunnypilot-build-model.yaml

* Update helpers.py

* Revert "Update helpers.py"

This reverts commit 3a955ca11a.

* Reapply "Update helpers.py"

This reverts commit ca9c6e1933.

* models: use less strict chestnut detection state

---------

Co-authored-by: Jason Wen <haibin.wen3@gmail.com>
2026-08-24 22:52:29 -04:00
Jason Wen 2ba91d2be5 ci: add tinygrad ref check to prepare_chestnut and even faster prebuilt stages (#1957)
* ci: faster prebuilt stages

* tg check chestnut

* zoomer!
2026-08-24 22:42:45 -04:00
Jason Wen 19f83b274f ci: identical environment for publish_chestnut prebuilt 2026-08-24 22:06:20 -04:00
Jason Wen d14d0b1dd0 ci: parallelize models chunk downloads and split branch publishing (#1955)
* ci: parallelize model chunk downloads and better publish

* ci: download all model chunks in parallel with xargs -P8

* split split

* ew

* must require
2026-08-24 21:48:53 -04:00
Jason Wen 6cc5f3aad8 ci: fix DM model build, separate HF defaults paths, nuke build races (#1956)
* ci: fix DM model build, separate HF defaults paths, nuke build races

* more split!

* name

* ci: download driving and DM model chunks into chestnut prebuilt output
2026-08-24 20:02:48 -04:00
Jason Wen 8e16c9babb ci: offload small model compilation (#1952)
* ci: compile default big model with stock modeld

* Revert "Revert big RL model (#38627)"

This reverts commit 516ec1e682.

* ci: compile default small model with stock modeld compiler

* ci: offload small model compilation

* Reapply "Revert big RL model (#38627)"

This reverts commit d06cfabb62.

* Reapply "Revert big RL model (#38627)"

This reverts commit d06cfabb62.
2026-08-24 16:24:19 -04:00
Jason Wen 2bcfed5c71 ci: compile default models with stock modeld (#1954)
* ci: compile default big model with stock modeld

* Revert "Revert big RL model (#38627)"

This reverts commit 516ec1e682.

* ci: compile default small model with stock modeld compiler

* Reapply "Revert big RL model (#38627)"

This reverts commit d06cfabb62.
2026-08-24 15:37:46 -04:00
DevTekVE 451cc3445a Bump opendbc 2026-08-23 16:35:28 +02:00
Jason Wen 1daa2d9081 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-08-17 10:29:01 -04:00
Jason Wen 7a9099818f Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-08-14 17:57:37 -04:00
Jason Wen ef4fa48f33 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-08-14 17:18:06 -04:00
Jason Wen e426ced4c0 bump 2026-08-11 17:47:18 -04:00
Jason Wen 7681ba763b Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-08-11 17:47:12 -04:00
Jason Wen b04d666a68 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-08-10 04:27:58 -04:00
Jason Wen fb026b86a3 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-08-06 21:58:57 -04:00
Jason Wen cff4c5e589 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-08-06 21:58:50 -04:00
Jason Wen e0cca951f3 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-07-25 08:52:04 -04:00
Jason Wen 2439c048ed Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-07-20 15:12:17 -04:00
Jason Wen 7b54d7d7a0 bump 2026-07-20 09:51:59 -04:00
Jason Wen b2bdb5787f Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
#	openpilot/tools/plotjuggler/layouts/analyzing-panda-block-angle-hkg.xml
#	openpilot/tools/plotjuggler/layouts/analyzing-torque-angle-hkg.xml
#	openpilot/tools/plotjuggler/layouts/hkg_angle_control.xml
#	openpilot/tools/plotjuggler/layouts/safety-limits-angle-kkg.xml
#	pyproject.toml
#	scripts/lint/lint.sh
2026-07-20 09:50:52 -04:00
Jason Wen 282f517b78 upstream changes 2026-06-09 00:18:40 -04:00
Jason Wen 1779144ff9 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
#	scripts/lint/lint.sh
2026-06-08 23:53:43 -04:00
Jason Wen 54fb2750ba Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-05-09 11:47:25 -04:00
DevTekVE 14431ab77f Merge branch 'master' into hkg-angle-steering-2025 2026-05-05 10:37:34 +02:00
Jason Wen 9d45db41b3 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
#	system/version.py
2026-05-03 16:08:40 -04:00
Jason Wen b57c593d92 bump 2026-04-20 23:31:05 -04:00
nayan 0674c42866 good bot
fix state
2026-04-19 08:52:19 +02:00
nayan 1f7bcf246a Bringing sl change to validate 2026-04-18 09:25:12 +02:00
DevTekVE b0512dc523 Revert "safety: dynamically relax lateral jerk limits during accel conflicts"
This reverts commit b0644a37e3b5a7b941bd4347f4c7ef0f25f44fbc.
2026-04-12 11:25:31 +02:00
DevTekVE cd88fd3850 Bringing shane's improvements on the angle steering branch 2026-04-10 12:09:12 +02:00
DevTekVE ff78eaeba1 Merge branch 'master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-04-10 11:38:19 +02:00
DevTekVE 92c8aeeb92 lint 2026-04-10 11:34:29 +02:00
DevTekVE ecaa20e7be Add source map configuration to VSCode launch settings
- Enables better debugging by mapping sources to `${workspaceFolder}/opendbc/safety`.
2026-04-05 15:10:21 +02:00
DevTekVE 859c98c9d8 Refactor PlotJuggler layouts and optimize custom math equations
- Introduced new tabs for `Smoothing and Torque ceilings`.
- Updated custom math equations for cleaner logic and added new snippets for angle smoothing, ceiling brackets, and roll compensation.
2026-04-05 12:14:13 +02:00
DevTekVE 69cbe8c6ed Enhance torque reduction logic with speed and steering error adjustments
- Introduced speed-dependent and error-sensitive dynamic torque ceilings.
- Improved interpolation for smoother torque application.
2026-04-04 11:55:14 +02:00
DevTekVE 1aafe92fc0 Remove hyundai_canfd_ccnc.dbc and update dependencies
- Deleted `_hyundai_canfd_ccnc.dbc` and its import references across related files.
- Merged relevant signals and comments into `hyundai_canfd_og.dbc` for consolidated usage.
- Cleaned up obsolete imports in `hyundai_canfd.dbc`.
2026-04-04 08:46:09 +02:00
DevTekVE adb6b9fb12 Test changing priority for reading dbc files to in memory first 2026-04-04 08:29:57 +02:00
DevTekVE f67a9f4624 Revised steering angle smoothing matrix and logic cleanup
- Adjusted `SMOOTHING_ANGLE_VEGO_MATRIX` to refine torque smoothing at mid-range speeds.
- Removed unused deadzone logic for cleaner and more consistent angle smoothing.
2026-04-03 18:10:05 +02:00
DevTekVE 094e834ac4 cleanup: remove unused datafile references and expand ignored patterns
- Deleted `<previouslyLoaded_Datafiles>` sections from PlotJuggler layouts to streamline configuration files.
- Added `.ipynb` files to the `pyproject.toml` ignore list for cleaner tooling.
2026-04-03 17:19:18 +02:00
DevTekVE e4067060b9 Adding ioniq 9 and updating ioniq 5 pe n-line fingerprint 2026-04-03 17:06:15 +02:00
DevTekVE 86a14640b5 Tune speed-dependent steering smoothing to eliminate EPS whine
Reimplemented an Exponential Moving Average (EMA) filter on the requested
steering angle (`apply_angle`). The model's raw high-frequency micro-corrections
at low speeds cause acoustic resonance (whine) in the EPS motor. This filter
dynamically adjusts the smoothing factor (alpha) based on vehicle speed to
silence the EPS at a crawl while maintaining zero-latency precision on the highway.

Key Behaviors & Speed Matrix:
* Deadzone: Ignores angle changes ≤ 0.1° to preserve straight-line tracking.
* 0 km/h (0 mph) -> Alpha: 0.05 (Max smoothing to eliminate stationary vibration)
* 30.6 km/h (19 mph) -> Alpha: 0.10 (Heavy smoothing for stable residential turning)
* 39.6 km/h (25 mph) -> Alpha: 0.30 (Moderate smoothing)
* 49.7 km/h (31 mph) -> Alpha: 0.60 (Light smoothing for responsive city driving)
* 80.0 km/h (50 mph) -> Alpha: 1.00 (Zero smoothing / raw signal for high-speed precision)
2026-04-03 16:13:05 +02:00
DevTekVE 59fb84f0d5 Remove HKG angle control tuning components and dependencies
- Deleted HKG-specific angle tuning settings and related UI elements.
    - Removed tuning parameter handling and smoothing logic from carcontroller.
    - Simplifies codebase and eliminates unused parameters.
2026-04-03 15:33:57 +02:00
DevTekVE 78de201ce7 Bring it back to 360 for hda1s 2026-04-03 15:14:37 +02:00
DevTekVE 17e49f69cc refactor: update parameterized tests and extend Hyundai Ioniq 5 PE model years
- Replaced `parameterized.expand` with new `parameterized` syntax for cleaner test definitions.
- Added 2026 model year to Hyundai Ioniq 5 PE in `car_list.json`.
2026-04-03 14:39:45 +02:00
DevTekVE bec75ebdd8 remove: TorqueReductionGainController and its associated tests
- Fully deprecates the no longer used torque reduction logic.
- Cleans up outdated functionality for clarity and maintainability.
2026-04-03 14:14:07 +02:00
DevTekVE 473832efa7 Merge branch 'master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-04-03 14:00:54 +02:00
DevTekVE 2cceeb3552 fix: clip steering angle to respect angle limits when latActive is off
- Prevents potential out-of-bound steering angle values.
- Ensures compliance with defined steering angle constraints.
2026-04-03 01:06:37 +02:00
DevTekVE 923a47f713 Reverting all the new control changes until we properly test them on a few variants to ensure it is safe.
Revert "upstream pending tune"

This reverts commit b51d9af9a0.

Revert "show torque reduction gain"

This reverts commit ded0b506d6.

Revert "must gate"

This reverts commit 8b60649eed.

Revert "bump"

This reverts commit 221c219fca.

Revert "temp: comment out blind-spot monitoring signals due to DBC changes"

This reverts commit 790a762a05.
2026-04-01 09:29:53 +02:00
DevTekVE 790a762a05 temp: comment out blind-spot monitoring signals due to DBC changes
- Avoided crash caused by missing signals in updated DBC definitions.
- Added a TODO to revisit and validate blind-spot logic.
2026-04-01 08:55:26 +02:00
Jason Wen 221c219fca bump 2026-03-31 21:57:58 -04:00
Jason Wen 8b60649eed must gate 2026-03-31 21:42:06 -04:00
Jason Wen ded0b506d6 show torque reduction gain 2026-03-31 07:46:13 -04:00
Jason Wen b51d9af9a0 upstream pending tune 2026-03-31 06:56:52 -04:00
Jason Wen 4460ce8166 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-03-18 03:43:10 -04:00
Jason Wen f1aa0c7f78 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-03-07 01:49:09 -05:00
Jason Wen e7c8126fd9 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-03-05 02:01:04 -05:00
Jason Wen 125999c364 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-03-01 16:34:41 -05:00
Jason Wen 5b25ea7f99 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-02-28 15:47:57 -05:00
Jason Wen b7e2631286 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-02-27 21:56:34 -05:00
Jason Wen a838871189 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-02-19 01:51:17 -05:00
Jason Wen 1827331599 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-02-17 20:12:13 -05:00
Jason Wen 5c777bbe01 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-02-13 23:41:06 -05:00
Jason Wen fb97f993d1 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-02-13 17:32:10 -05:00
Jason Wen 94b67077e3 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-02-12 23:35:46 -05:00
Jason Wen 14f17699b9 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-02-11 00:35:20 -05:00
Jason Wen 80e27d5cbb Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-02-10 23:41:27 -05:00
Jason Wen 039dbcd877 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-02-09 01:46:00 -05:00
Jason Wen 8c134ae555 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-02-08 20:04:01 -05:00
Jason Wen 276c7a2b34 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-02-02 22:40:14 -05:00
Jason Wen 0e2dbcebfa Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-01-26 11:45:29 -05:00
Jason Wen bbb7760a95 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2026-01-19 01:43:21 -05:00
Jason Wen 23a27b2fbf Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2026-01-09 18:48:43 -05:00
Jason Wen 8b78107a40 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2025-12-31 00:49:56 -05:00
Jason Wen c27b6007de wrong bump? 2025-12-26 10:08:31 -05:00
Jason Wen 36c2dce247 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2025-12-26 10:08:23 -05:00
Jason Wen 8035039731 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-12-23 00:52:24 -05:00
Jason Wen 8aa6c9440f Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2025-12-20 17:01:25 -05:00
Jason Wen 34ef40fd81 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-12-18 00:19:20 -05:00
Jason Wen 4d044d7618 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2025-12-15 02:25:04 -05:00
Jason Wen 6247e3dc84 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-12-13 01:59:06 -05:00
Jason Wen b1131289b7 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2025-12-07 01:37:16 -05:00
Jason Wen 35dc7d661e Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2025-12-07 00:11:54 -05:00
DevTekVE c39b2dad94 Merge branch 'master' into hkg-angle-steering-2025 2025-11-29 10:12:31 +01:00
Jason Wen e6b769245c Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
#	selfdrive/ui/sunnypilot/SConscript
#	selfdrive/ui/sunnypilot/qt/offroad/settings/lateral_panel.cc
#	selfdrive/ui/sunnypilot/qt/offroad/settings/lateral_panel.h
#	selfdrive/ui/sunnypilot/qt/offroad/settings/longitudinal_panel.cc
2025-11-25 18:54:02 -05:00
DevTekVE 8b94f8b2f8 Merge branch 'master' into hkg-angle-steering-2025 2025-11-06 18:31:16 +01:00
Jason Wen dec014cd17 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	sunnypilot/selfdrive/car/interfaces.py
2025-11-04 17:45:05 -05:00
DevTekVE 7b40272866 Add sunnypilot-specific stats logging and handling
- Introduced `StatLogSP` for sunnypilot-specific metrics.
- Integrated stats collection and submission pathways for sunnylink.
- Extended parameters and handlers to support additional metrics.
- Added gzip compression and base64 encoding for oversized payload handling.
2025-11-04 21:20:16 +01:00
DevTekVE 506456e7f0 Merge branch 'master' into hkg-angle-steering-2025 2025-11-01 13:31:23 +01:00
DevTekVE 4ea4b9d177 Merge branch 'master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-10-31 06:59:39 +01:00
DevTekVE 0e2313dc31 Merge branch 'master' into hkg-angle-steering-2025 2025-10-18 11:14:45 +02:00
Jason Wen 79ea7db103 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2025-10-17 23:42:01 -04:00
Jason Wen f9ae9192fa Merge branch 'ui-icbm-universal' into hkg-angle-steering-2025 2025-10-17 21:55:00 -04:00
Jason Wen 7ec23006c6 check this 2025-10-17 21:54:44 -04:00
Jason Wen 2be9447a6c Merge branch 'ui-icbm-universal' into hkg-angle-steering-2025 2025-10-17 21:19:09 -04:00
Jason Wen cfd926778e always init true 2025-10-17 21:19:03 -04:00
Jason Wen a97a67e3d0 need 2025-10-17 21:17:31 -04:00
Jason Wen 518b6de08d Merge branch 'ui-icbm-universal' into hkg-angle-steering-2025 2025-10-17 21:15:59 -04:00
Jason Wen 6933e3bcdb fix cruise toggles 2025-10-17 21:15:43 -04:00
Jason Wen 05e0ca8bee some more 2025-10-17 20:46:36 -04:00
Jason Wen 410614fcf3 single location 2025-10-17 20:26:18 -04:00
Jason Wen e2bc0996ef Merge branch 'ui-icbm-universal' into hkg-angle-steering-2025 2025-10-17 12:21:47 -04:00
Jason Wen 1be0c20cf5 oops 2025-10-17 12:21:37 -04:00
Jason Wen 839143b9ed oops 2025-10-17 12:20:23 -04:00
Jason Wen bce86637ae Merge branch 'ui-icbm-universal' into hkg-angle-steering-2025 2025-10-17 12:15:23 -04:00
Jason Wen b833d3ee89 ui: update ICBM-related settings handling 2025-10-17 12:14:44 -04:00
Jason Wen e0441dfb4b Merge branch 'sla-event' into hkg-angle-steering-2025 2025-10-17 11:58:42 -04:00
Jason Wen 62ec40bba6 Speed Limit Assist: update active event handling 2025-10-17 11:58:19 -04:00
Jason Wen 15c6d38028 bump 2025-10-16 17:05:58 -04:00
Jason Wen 56eb9f555c Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	sunnypilot/selfdrive/controls/lib/e2e_alerts_helper.py
2025-10-16 01:12:10 -04:00
Jason Wen 2f9951df02 Merge branch 'e2e-alert-state-machine' into hkg-angle-steering-2025 2025-10-15 23:55:40 -04:00
Jason Wen 6030bf4da3 less 2025-10-15 23:52:03 -04:00
Jason Wen 074694d660 lead depart: only arm if we have a confirmed close lead for over a second after allowing alert 2025-10-15 23:48:13 -04:00
Jason Wen df35f48f3b magic 2025-10-15 22:56:08 -04:00
Jason Wen 4fb9704540 time based 2025-10-15 22:51:40 -04:00
Jason Wen 48cbe266fc 10 frames for both 2025-10-15 22:50:42 -04:00
Jason Wen 21aa7ff367 rename 2025-10-15 22:47:08 -04:00
Jason Wen 7caf05dd51 not used 2025-10-15 22:41:00 -04:00
Jason Wen 2d779f5db9 E2E Helper: universal state machine 2025-10-15 22:38:57 -04:00
Jason Wen 18208f1da0 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2025-10-15 17:41:56 -04:00
Jason Wen 5a3c6ddf57 gate lka angle steering out of alpha long 2025-10-14 23:25:00 -04:00
Jason Wen eaa8732ab0 Merge branch 'e2e-alerts-cooldown' into hkg-angle-steering-2025 2025-10-14 14:44:00 -04:00
Jason Wen 6f0284c84f try preventing startup false trigger 2025-10-14 14:43:47 -04:00
Jason Wen 999ea03f23 try preventing startup false trigger 2025-10-14 14:42:42 -04:00
Jason Wen 0975db3ff1 Merge branch 'e2e-alerts-cooldown' into hkg-angle-steering-2025 2025-10-14 14:31:59 -04:00
Jason Wen 8d70a8b80a only when long not engaged 2025-10-14 14:31:48 -04:00
Jason Wen da93f92887 rename 2025-10-14 14:26:57 -04:00
Jason Wen 9117f6c071 Merge branch 'e2e-alerts-cooldown' into hkg-angle-steering-2025 2025-10-14 14:23:46 -04:00
Jason Wen 3567ff9691 introduce recent moving check 2025-10-14 14:22:41 -04:00
Jason Wen f44ae2ced9 too complicated 2025-10-14 14:08:40 -04:00
Jason Wen 376e0ca615 only allow one trigger per standstill session 2025-10-14 14:07:16 -04:00
Jason Wen 32b7686468 Merge branch 'master' into e2e-alerts-cooldown 2025-10-14 11:40:58 -04:00
nayan b9e0f52ea9 E2E Alert Cooldown 2025-10-14 07:43:15 -04:00
Jason Wen a3163b680f Merge branch 'sla-chimes' into hkg-angle-steering-2025 2025-10-14 02:01:05 -04:00
Jason Wen 8a927d808f Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-10-14 02:00:36 -04:00
Jason Wen bc7d5e474d Speed Limit Assist: audible alerts for certain states 2025-10-14 01:45:13 -04:00
Jason Wen 36f192b5fe Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2025-10-13 03:10:47 -04:00
Jason Wen ffd5cd4ac2 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2025-10-11 02:29:47 -04:00
Jason Wen e4a00fcd6c Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025 2025-10-10 17:28:16 -04:00
Jason Wen 0bdcb41103 Merge remote-tracking branch 'sunnypilot/sunnypilot/master' into hkg-angle-steering-2025
# Conflicts:
#	common/params_keys.h
#	opendbc_repo
#	selfdrive/ui/sunnypilot/qt/offroad/settings/lateral_panel.cc
2025-10-10 17:02:14 -04:00
DevTekVE 78051085ca Merge branch 'master' into hkg-angle-steering-2025 2025-09-23 07:54:32 +02:00
DevTekVE 4910d5809a bump opendbc 2025-09-23 07:45:39 +02:00
DevTekVE 8dd862ff28 yikes, becoming picky huh? 2025-09-14 22:50:21 +02:00
DevTekVE 1b57497da9 Merge remote-tracking branch 'origin/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-09-14 22:48:00 +02:00
DevTekVE 8d8d1ffc7a bump opendbc again 2025-09-14 22:46:20 +02:00
DevTekVE c5919d5495 wrong dbc lol 2025-09-14 22:42:19 +02:00
DevTekVE da71951c95 This is no longer in use nor needed. Bai! 2025-09-14 12:56:28 +02:00
DevTekVE 25a152cd8b Merge remote-tracking branch 'origin/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-09-14 12:44:23 +02:00
DevTekVE 9077a1082a Sorry for C3 :( but moving you out to a last working branch before I sync it up 2025-09-14 06:52:24 +02:00
DevTekVE 7ae7000254 Rework override behavior and feeling 2025-09-14 06:38:00 +02:00
DevTekVE 7029455706 better juggle 2025-09-13 08:32:27 +02:00
DevTekVE 3a71a62215 Merge branch 'master' into hkg-angle-steering-2025 2025-09-12 10:14:52 +02:00
DevTekVE 00622e8c33 Merge remote-tracking branch 'origin/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-09-05 09:46:41 +02:00
DevTekVE 549da3ee92 Merge branch 'master' into hkg-angle-steering-2025 2025-09-04 20:20:37 +02:00
DevTekVE e038a65ef8 Merge branch 'master' into hkg-angle-steering-2025 2025-08-31 13:14:33 +02:00
DevTekVE 8d0513c657 dbc: update CHECKSUM format for multiple messages to improve data integrity 2025-08-30 19:56:21 +02:00
DevTekVE 2cea48f4cd Merge remote-tracking branch 'origin/master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-08-30 15:27:45 +02:00
DevTekVE 8855a9ab65 Improve surprise jerk by safety blocks 2025-08-26 14:47:26 +02:00
DevTekVE 32321c01cc A bit more helpful safety block investigation help 2025-08-26 10:09:11 +02:00
DevTekVE 52cd65fefb lint dont bother me 2025-08-25 08:24:24 +02:00
DevTekVE 1fcdeccd40 Merge branch 'master' into hkg-angle-steering-2025
# Conflicts:
#	common/params_keys.h
#	opendbc_repo
2025-08-25 08:01:51 +02:00
DevTekVE 3517c36978 Revert "Add HkgAngleDebug structure and enhance angle debugging in car controller" 2025-08-24 19:02:48 +02:00
DevTekVE fb30c3c1e8 cleanup and honour params 2025-08-23 15:42:47 +02:00
DevTekVE 1c25e568d5 Update steering pressed logic to include hands-on-wheel detection for improved safety 2025-08-23 15:11:07 +02:00
DevTekVE f172122b7c Update steering pressed logic to include hands-on-wheel detection for improved safety 2025-08-22 19:55:16 +02:00
Jason Wen 67d6cdc7cd Merge remote-tracking branch 'sunnypilot/sunnypilot/hkg-angle-steering-2025' into hkg-angle-steering-2025 2025-08-21 16:39:36 -04:00
DevTekVE 6724085cfd Refactor angle limit calculations and adjust average road roll for improved steering dynamics 2025-08-21 20:09:57 +02:00
DevTekVE 6774f34eee Refine non-linear mapping in torque reduction gain calculation for improved steering response 2025-08-21 00:21:46 +02:00
DevTekVE 6d0402896d Adjust STEER_THRESHOLD and refine non-linear mapping in torque reduction gain calculation for improved steering response 2025-08-20 23:16:04 +02:00
DevTekVE 344021a3d9 Adjust non-linear mapping in torque reduction gain calculation for improved response 2025-08-20 19:54:31 +02:00
DevTekVE a9b85ab27d Refactor HkgAngleDebug structure to include current and baseline limits for angle parameters 2025-08-20 19:54:10 +02:00
DevTekVE 17204a46e4 Add HkgAngleDebug structure and enhance angle debugging in car controller 2025-08-20 18:39:53 +02:00
DevTekVE 7c4d415462 Enhance torque reduction gain calculation with non-linear mapping and smoothing 2025-08-20 00:12:43 +02:00
DevTekVE b8985b6d72 Enhance torque reduction gain calculation with non-linear mapping and smoothing 2025-08-19 19:50:13 +02:00
DevTekVE c669473f88 Refine torque reduction parameters and update UI for angle error analysis 2025-08-19 19:35:34 +02:00
DevTekVE 8751435bf5 Improving tq redc gain and override behavior 2025-08-19 10:08:51 +02:00
DevTekVE 30ae210761 Merge branch 'master' into hkg-angle-steering-2025 2025-08-19 10:07:42 +02:00
Jason Wen 3eb693f58b Merge remote-tracking branch 'sunnypilot/sunnypilot/hkg-angle-steering-2025' into hkg-angle-steering-2025 2025-08-18 12:30:29 -04:00
DevTekVE 7b4a31c5ac bugfix 2025-08-17 16:07:45 +02:00
DevTekVE 1527c8cf88 bump opendbc 2025-08-17 15:31:31 +02:00
DevTekVE ab0a7ae666 no joystick on this branch, causing issues 2025-08-17 15:25:40 +02:00
DevTekVE 11ec2f1f21 Apply suggestions from code review 2025-08-17 15:10:17 +02:00
DevTekVE 2c6808d37e Merge branch 'master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-08-17 15:02:28 +02:00
Jason Wen 2e96382c49 notebook init 2025-08-17 00:34:01 -04:00
DevTekVE 0239e440ca Adjust replay 2025-08-15 10:32:07 +02:00
Jason Wen 76b972daff Hyundai angle steering: STEERING_ANGLE_2 available on all cars 2025-08-14 01:56:46 -04:00
Jason Wen bc3ef3e7dd Hyundai angle steering: hugging no more - use the true steering angle signal from MDPS 2025-08-13 23:08:32 -04:00
DevTekVE 9839291dd0 Merge remote-tracking branch 'origin/master' into hkg-angle-steering-2025 2025-08-13 20:13:42 +02:00
DevTekVE 17cba328d6 refactor: update torque tuning configuration for angle steering
- Adjusted torque tuning configuration to avoid reliance on torque controller for Hyundai angle steering.
- Simplified control logic by removing unnecessary checks for torque control type.
refactor: clean up code formatting and improve test structure for torque reduction gain
2025-08-13 20:03:51 +02:00
DevTekVE 86093765d8 Merge branch 'master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-08-13 07:55:46 +02:00
DevTekVE 05fa1c8ae8 Adjust default params and cleanup 2025-08-12 21:36:22 +02:00
DevTekVE e8a40d6b85 Merge branch 'master' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
#	system/manager/process_config.py
2025-08-10 14:24:10 +02:00
DevTekVE c265e0bb85 Merge remote-tracking branch 'origin/master' into hkg-angle-steering-2025
# Conflicts:
#	common/params_keys.h
#	opendbc_repo
#	system/manager/manager.py
2025-08-02 09:56:58 +02:00
DevTekVE c6b118788b Merge branch 'master-new' into hkg-angle-steering-2025 2025-07-31 18:25:08 +02:00
DevTekVE b004f6dbdc Merge branch 'master-new' into hkg-angle-steering-2025 2025-07-31 18:17:34 +02:00
DevTekVE cd4930b680 Bump opendbc 2025-07-26 10:56:49 +02:00
DevTekVE f861aca628 Refactor vehicle model initialization and adjust angle limits for baseline model 2025-07-26 08:12:06 +02:00
DevTekVE 1ff0d8e2ee please don't bother me anymore! 2025-07-26 08:09:51 +02:00
DevTekVE d76d70764e Update slip factor precision for Hyundai steering parameters
- Adjusted `slip_factor` in Hyundai CANFD safety modes for improved consistency and accuracy.
- Ensured proper representation of `slip_factor` output in test logs.
2025-07-25 20:17:19 +02:00
DevTekVE dc73ce0b71 save tools replay 2025-07-25 19:47:31 +02:00
DevTekVE 3f666748af bump opendbc 2025-07-25 14:16:02 +02:00
DevTekVE 8de8a8838c bumo opendbc 2025-07-25 14:08:53 +02:00
DevTekVE f563b7eb71 Refactor steering angle limit application for improved safety and model compliance 2025-07-25 12:12:42 +02:00
DevTekVE 3c18b83708 save temp 2025-07-25 09:56:30 +02:00
DevTekVE bd35f5904b Enhance steering angle rate limiting and safety enforcement logic
- Introduced explicit post-rate limiting using model-specific dynamics.
- Improved low-speed smoothing and precision of applied angles.
2025-07-25 08:12:41 +02:00
DevTekVE 474f2737f6 Refactor steering angle limit logic for conservative seleion
- Removed unused lateral accel/jerk logic for simplicity.
- Updated angle limit calculations to choose the smallest delta for safer control.
2025-07-24 21:48:24 +02:00
DevTekVE ea1ac4a212 Revert "Add configurable max lateral accel and jerk parameters for Hyundai vehicles"
This reverts commit b95f8c5929.

Revert "Add baseline safety model and improve steering angle limiting logic"

This reverts commit b53cbb2e18.

Revert "Disable lateral accel/jerk params and ensure float consistency in angle limits"

This reverts commit 165d7c7b36.
2025-07-24 10:02:48 +02:00
DevTekVE 165d7c7b36 Disable lateral accel/jerk params and ensure float consistency in angle limits
- Commented out unused lateral accel/jerk parameters for clarity.
- Ensured `np.clip` always returns a float for precision.
2025-07-24 09:41:52 +02:00
DevTekVE b53cbb2e18 Add baseline safety model and improve steering angle limiting logic
- Introduced a baseline safety model (`GENESIS_GV80_2025`) for comparison.
- Enhanced steer angle limit calculation using both baseline and current limits for improved safety and precision.
2025-07-24 09:38:03 +02:00
DevTekVE b95f8c5929 Add configurable max lateral accel and jerk parameters for Hyundai vehicles
- Introduced user-configurable options for max lateral acceleration and jerk.
- Enables fine-tuning of vehicle handling for smoother control.
2025-07-24 08:39:10 +02:00
DevTekVE e564bb0b85 bumo openbc 2025-07-23 18:46:52 +02:00
DevTekVE e2ec8a7b13 Refine lateral control limits and simplify safety model handling
- Reduced max lateral acceleration and jerk by 20% for smoother handling.
- Removed unused `get_safety_CP` function, simplifying `VehicleModel` initialization.
2025-07-22 08:07:51 +02:00
DevTekVE 75c6f0f10e Test with gv80 as baseline for limits 2025-07-20 22:14:18 +02:00
DevTekVE af38044b42 Merge branch 'master-new' into hkg-angle-steering-2025 2025-07-20 10:14:46 +02:00
DevTekVE 684fa846d8 Merge branch 'master-new' into hkg-angle-steering-2025
# Conflicts:
#	.codespellignore
#	opendbc_repo
#	system/manager/manager.py
2025-07-19 21:51:46 +02:00
DevTekVE 416e722855 Update baseline model to IONIQ 5 PE for improved angle safety tuning
- Replaced conservative GENESIS_GV80_2025 model with IONIQ 5 PE parameters.
- Adjusted steering parameters (ratio, slip factor, wheelbase) for better lateral control performance.
2025-07-19 21:46:17 +02:00
DevTekVE 9fd4613bbb Add 2025 Kia EV6 support with updated radar and camera fingerprints 2025-07-09 09:47:31 +02:00
DevTekVE a0362e3c5f "Refined UI labels and tooltips for HKG tuning options to improve clarity and user understanding." 2025-06-29 16:48:53 +02:00
DevTekVE e32ef1cdc0 Fix incorrect torque sign usage in torque reduction calculation
Ensure `actuators.torque` uses its absolute value in the `calculate_angle_torque_reduction_gain` method to prevent sign-related issues during Hyundai steering angle control.
2025-06-29 14:33:30 +02:00
DevTekVE 20673ec8a6 Adjust warning font size in angle tuning settings panel. 2025-06-29 13:35:09 +02:00
DevTekVE 53fbdf7329 Rename "IdleTorque" to "ActiveTorque" for clarity.
The parameter name "HkgTuningAngleIdleTorqueReductionGain" was updated to "HkgTuningAngleActiveTorqueReductionGain" across multiple files for better clarity and alignment with its functionality. This change ensures consistency in naming conventions and improves code readability.
2025-06-29 13:23:56 +02:00
DevTekVE 6f72b74fac Add idle torque reduction for Hyundai lateral control
Introduced `ANGLE_IDLE_TORQUE_REDUCTION_GAIN` to manage torque when the vehicle is stationary, ensuring smoother handling and better lane centering. Updated parsing, parameters, and UI settings to support this new idle torque parameter. Adjusted torque calculation logic and smoothing factor behavior for enhanced control flexibility.
2025-06-29 13:22:18 +02:00
DevTekVE e83705a32e Merge branch 'master-new' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-06-29 09:44:01 +02:00
DevTekVE 95d36b9ba2 Refactor and enhance HKG angle tuning logic.
Introduced a toggle for angle smoothing factor and renamed related parameters for clarity. Refactored backend settings to use new parameter names and expanded smoothing matrices for better tuning granularity. Updated UI elements to reflect these changes, emphasizing usability and consistency.
2025-06-28 21:25:44 +02:00
DevTekVE b9e74254bd Merge branch 'master-new' into hkg-angle-steering-2025 2025-06-27 10:46:22 +02:00
DevTekVE b4405b200d Merge remote-tracking branch 'origin/master-new' into hkg-angle-steering-2025 2025-06-25 09:27:21 +02:00
DevTekVE a8a3fdac54 Rename parameter in calculate_target_torque for clarity. 2025-06-23 22:53:45 +02:00
DevTekVE 4eddc622a7 Refactor torque calculations in Hyundai controller
Rename methods and variables for clarity in torque reduction and override calculations. Adjust logic to streamline handling of steering inputs and improve maintainability.
2025-06-23 22:51:40 +02:00
DevTekVE 4e42ada240 Refactor torque management in Hyundai controller for cleaner override and ramp logic
Extract torque ramping and override functionality into dedicated methods within `LkasTorqueManager` to improve maintainability and reduce redundancy. Simplify `update` logic by delegating state-specific operations to new methods.
2025-06-23 22:47:51 +02:00
DevTekVE 6266217655 Introduce LkasTorqueManager for LKAS torque handling in Hyundai controller
Encapsulate LKAS torque calculations, ramping, and override logic into the new `LkasTorqueManager` class to improve modularity and maintainability. Replace existing torque logic with calls to the manager.
2025-06-23 22:20:10 +02:00
DevTekVE ea09d32e98 Remove lateral acceleration logic from Hyundai steering controller 2025-06-23 21:55:17 +02:00
DevTekVE 15958c88d3 Refactor lateral acceleration scaling logic in Hyundai controller
Move scaling of `max_angle_delta` under high lateral acceleration to improve clarity and prevent redundant operations.
2025-06-23 20:22:03 +02:00
DevTekVE b80d7fb5ea Adding GV70 electrified 2026 2025-06-22 14:30:59 +02:00
DevTekVE 1c3d25c6ff Refine lateral acceleration handling in Hyundai steering logic
Enforce absolute check for `real_a_lat` against `MAX_LATERAL_ACCEL` to improve angle scaling under high lateral acceleration conditions.
2025-06-22 11:03:35 +02:00
rav4kumar c9f22b32c7 Revert "Incorporate lateral acceleration in Hyundai angle steering logic"
This reverts commit c0524985bb.
2025-06-21 11:40:58 -07:00
DevTekVE c0524985bb Incorporate lateral acceleration in Hyundai angle steering logic
Add handling for IMU lateral acceleration to refine steering angle limits in CAN FD configurations. Parse and utilize `IMU_LatAccelVal` signal for enhanced lateral control accuracy.
2025-06-21 17:34:13 +02:00
DevTekVE 83839c7ea7 Add angle steering support and refactor related logic for Hyundai CAN FD.
Introduced support for CAN FD angle steering, including updated parameters, signal parsing, and new tests. Refactored related steering logic for clarity, reducing unused code and enhancing maintainability.
2025-06-21 13:38:50 +02:00
DevTekVE c1a1d4b4c3 Update lint script to exclude .xml files in layouts directory
Added `layouts/.*\.xml` to `IGNORED_FILES` in `lint.sh` to prevent linting of layout XML files.
2025-06-20 10:50:45 +02:00
DevTekVE b5af7a905a Merge branch 'master-new' into hkg-angle-steering-2025 2025-06-18 20:13:45 +02:00
DevTekVE 96b1b2f55f Update steering request logic in Hyundai controller
Ensure steering request activation depends on lateral control being active. This adds clarity and aligns better with control logic requirements.
2025-06-17 18:51:54 +02:00
DevTekVE 9361ba5d70 Refactor Hyundai steering angle handling logic
Streamline steering angle calculations and fault avoidance logic by removing redundant comments and unused code. Simplified `round_angle` implementation for clarity and consistency.
2025-06-17 12:08:06 +02:00
DevTekVE 4e9014311e Refactor steeringPressed logic in Hyundai carstate.py.
Revised the determination of `steeringPressed` to account for both hands-on-wheel detection and torque overriding in CAN FD setups. Simplified fallback logic for non-CAN FD configurations for better code clarity and maintainability.
2025-06-12 00:31:07 +02:00
DevTekVE 232873fc70 Refine steering press detection logic.
Adjusted the sensitivity and threshold values for `HOD_Dir_Status` in steering press updates, improving accuracy in detecting steering input. This change aligns with updated parameter requirements for better responsiveness.
2025-06-12 00:14:05 +02:00
DevTekVE 0a61fca9c9 Fix steering press detection for Hyundai models.
Updated the condition to detect steering press by changing HOD_Dir_Status threshold from `> 2` to `>= 2`. This ensures the detection logic aligns correctly with expected behavior.
2025-06-12 00:06:52 +02:00
DevTekVE 480bdc34dc Add support for CANFD angle steering in Hyundai cars
Introduced handling for the `HOD_FD_01_100ms` message when the CANFD angle steering flag is enabled. This ensures proper message parsing and extends compatibility for specific Hyundai vehicle configurations.
2025-06-12 00:04:44 +02:00
DevTekVE 716b475a13 Update Hyundai controls for HOD status and steer limits
Adjusted the steering override frame window and incorporated new HOD_Dir_Status to improve hands-on detection. Added parsing for new signals in Hyundai CAN FD, enhancing steering override responsiveness and reliability.
2025-06-12 00:01:31 +02:00
DevTekVE b1ec5ec034 Adjust override angle cap in Hyundai car controller
Increased the minimum override angle cap from 0.01 to 0.1 and explicitly cast the maximum cap to a float. This change improves consistency and ensures proper handling of steering limits.
2025-06-11 23:20:19 +02:00
DevTekVE 470613c2b7 Adjust Hyundai steer override parameters for improved control.
Reduced the override frame window and updated the angle cap logic to use MAX_ANGLE_RATE. These changes aim to enhance steering responsiveness and safety by fine-tuning steer angle limits.
2025-06-11 23:07:49 +02:00
DevTekVE 336c5b4154 Remove smoothing_factor from Hyundai car controller logic
The `smoothing_factor` parameter and related logic have been removed to simplify the steering angle smoothing approach. All references and usage of this parameter have been eliminated, relying solely on speed-based dynamic interpolation. This change streamlines the code while maintaining functionality.
2025-06-11 23:04:32 +02:00
DevTekVE abdb9dc750 Adjust Hyundai steering override frame logic
Reduced `OVERRIDE_FRAME_WINDOW` and updated condition to properly respect override frame limits. This ensures smoother handling and more precise steering adjustments under certain driving scenarios.
2025-06-11 22:49:04 +02:00
DevTekVE ab98683973 Refactor steering override logic in Hyundai carcontroller
Replaced `recently_overridden` with `frames_since_override` for better granularity and added dynamic override angle limits using interpolation. These changes enhance steering control accuracy during user overrides and improve overall code readability.
2025-06-11 22:42:05 +02:00
DevTekVE 186c24dbe6 Refine Hyundai steering override handling logic
Adjusted logic for recently overridden steering to improve angle limits and torque smoothing. Removed unused or redundant code, optimizing the functionality and maintaining cleaner readability.
2025-06-11 21:49:18 +02:00
DevTekVE 9cdf6340a1 Refactor steering angle smoothing for clarity and reuse.
Extracted the steering angle smoothing logic into a standalone function `sp_smooth_angle` to enhance readability and reusability. Adjusted angle smoothing parameters and introduced a maximum vehicle speed threshold for applying smoothing. Minor updates improve maintainability and ensure consistent behavior across speed ranges.
2025-06-11 10:07:44 +02:00
DevTekVE 2855b1341c Adjust steering thresholds for Hyundai CAN FD vehicles
Updated `STEER_THRESHOLD` to 350 and `NO_LONGER_OVERRIDING_THRESHOLD` to 150 for better alignment with Hyundai CAN FD steering behavior. These changes ensure improved compatibility and more accurate steering response.
2025-06-10 09:53:08 +02:00
DevTekVE cf28f99976 Revert "Add twilsonco's LKAS torque calculator for improved lateral control"
This reverts commit b1770fb0e7aece0e160b1b083cb260edbbdc53dd.
2025-06-10 09:40:59 +02:00
DevTekVE a39d67dc47 Fix apply_angle_last reset logic in Hyundai carcontroller
Re-enables resetting `apply_angle_last` to `steering_angle` when steering is recently overridden. This ensures proper handling of steering angle limits during transitions.
2025-06-08 19:04:02 +02:00
DevTekVE 7e75257f12 Refine Hyundai steering control logic.
Simplified torque ramp-up logic by combining conditions and adjusted `STEER_THRESHOLD` for CANFD angle steering. These changes aim to enhance control precision and maintain consistency in overrides.
2025-06-08 19:02:49 +02:00
DevTekVE df38449553 Reduce override timeout for Hyundai carcontroller
Decrease the override timeout from 100 to 50 frames, ensuring quicker recognition of driver input override. This improves responsiveness and aligns with refined control behavior.
2025-06-08 18:22:44 +02:00
DevTekVE 1385ef3bc5 Fix steering control behavior during user override
Removed restrictive rate limiting during recent user overrides to improve steering response. Adjusted logic to ensure correct handling of steering angle when lateral control is inactive or overridden.
2025-06-08 18:01:47 +02:00
DevTekVE 7c23c11c51 Refine steering logic with override detection.
Adjust steering behavior to account for recent user overrides, improving safety and control. Introduced a "recently_overridden" check to limit angle rates and torque adjustments when user intervention is detected.
2025-06-08 17:52:16 +02:00
DevTekVE aeff2e12ec Refine steering logic with user override handling.
Added logic to use the current steering angle when the steering wheel is pressed, ensuring smoother transitions during user overrides. Updated function parameters and implementation to reflect this enhancement.
2025-06-08 17:38:34 +02:00
DevTekVE 7274899671 Refactor Hyundai override logic for steering thresholds
Removed redundant `recently_overridden` logic and introduced a more robust approach for tracking user steering overrides. Added `NO_LONGER_OVERRIDING_THRESHOLD` and updated conditions to improve steer override handling. Adjustments ensure smoother torque transitions and more accurate steering state detection.
2025-06-08 17:00:44 +02:00
DevTekVE 6c00fd608f pass tests? 2025-06-08 12:28:11 +02:00
DevTekVE df6a034c11 Bump opendbc 2025-06-08 12:26:09 +02:00
DevTekVE acb109c290 adding plotjuggler stuff 2025-06-08 10:02:44 +02:00
DevTekVE b227b00249 Update torque clamping to use parameterized min torque
Replaced hardcoded `angle_min_active_torque` with `ANGLE_MIN_TORQUE` from params for better configurability and consistency. This ensures the torque clamping logic aligns with defined parameters.
2025-06-07 19:43:01 +02:00
DevTekVE 3ec9d6c18a Merge branch 'master-new' into hkg-angle-steering-2025
# Conflicts:
#	common/params_keys.h
2025-06-07 15:04:16 +02:00
DevTekVE 86db8b95f0 Refactor torque calculation and deactivate live tuning.
Updated torque calculation logic with a new optional parameter for minimum active torque, streamlining control behavior. Deactivated and cleaned up references to HkgAngleLiveTuning, simplifying configuration and reducing runtime complexities. Updated relevant UI and parameter descriptions for clarity.
2025-06-07 11:55:57 +02:00
DevTekVE 4cfff8a35f Merge branch 'master-new' into hkg-angle-steering-2025 2025-06-06 23:08:37 +02:00
DevTekVE 962fedf48c Merge branch 'master-new' into hkg-angle-steering-2025
# Conflicts:
#	opendbc/car/tests/routes.py
2025-06-06 20:49:06 +02:00
DevTekVE 04494414d1 Merge branch 'master-new' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-06-05 09:18:53 +02:00
DevTekVE 0b83576e9b Adjust torque ramping logic and update steering thresholds
Increase the override window and refine torque ramp-up behavior to avoid conflicts during recent overrides. Updated steering driver allowance and threshold values for CANFD angle steering to improve compatibility and performance.
2025-06-02 09:49:31 +02:00
DevTekVE ce4ef0f817 Refine steering override logic in Hyundai car controller
Added logic to track recent steering overrides and adjust LKAS torque behavior accordingly. This ensures smoother transitions when the steering is overridden and reduces potential conflicts with driver input. Updated CANFD-specific steering thresholds for enhanced compatibility.
2025-06-02 09:12:03 +02:00
DevTekVE f0b15c1c56 Adding twil's torque calculation 2025-06-01 19:04:34 +02:00
DevTekVE f898e9fdfe Merge branch 'master-new' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-06-01 09:46:45 +02:00
DevTekVE 8ee7804b0e Bump opendbc (no tesla controls, no twil yet) 2025-05-29 16:31:42 +02:00
DevTekVE 923228194e bump opendbc to prior tesla changes until i can pass safety validations 2025-05-28 12:44:44 +02:00
DevTekVE 8837b2e3f6 Merge branch 'master-new' into hkg-angle-steering-2025
# Conflicts:
#	opendbc_repo
2025-05-28 12:36:02 +02:00
DevTekVE f48c9dc1c2 bump opendbc 2025-05-25 17:34:24 +02:00
DevTekVE 74aa07a8cd Ingore something i dont control thx 2025-05-25 17:31:37 +02:00
DevTekVE 5236e4860f Make lint happy, maybe 2025-05-25 17:31:37 +02:00
DevTekVE 3d174da1c3 adding some of my tests and validaitons 2025-05-25 17:31:25 +02:00
DevTekVE 8faa40f3a3 clean 2025-05-25 17:31:25 +02:00
DevTekVE 3e03275f28 Add PlotJuggler layout for analyzing torque and angle data
This new layout visualizes actuator data, CAN steering messages, and car state variables. It provides multiple time-series plots to aid in debugging and analysis. Plugin configurations are also included for extended functionality.
2025-05-25 17:31:22 +02:00
DevTekVE 7595cf8a25 Refine Hyundai angle and torque control logic.
Simplified control flag handling for angle steering, adjusted torque calculations for smoother ramp rates, and updated tuning parameters for the Hyundai Ioniq 5 PE. Minor adjustment to return value handling in lateral control functions.
2025-05-25 17:31:22 +02:00
DevTekVE 2675d43adb bump opendbc
Remove duplicate STEER_ANGLE_SATURATION_THRESHOLD import

Cleaned up an unnecessary duplicate import of STEER_ANGLE_SATURATION_THRESHOLD from latcontrol_angle_torque. This simplifies the module imports and prevents potential redundancy or confusion.

Refactor lateral control to combine torque and angle logic

Merged functionalities of LatControlTorque and LatControlAngle into a single LatControlAngleTorque class. Refactored code to utilize methods from both parent classes, reducing duplication and improving maintainability.

Add angle-torque hybrid lateral control for Hyundai CAN FD

Introduces `LatControlAngleTorque` to enable hybrid angle and torque-based steering for specific Hyundai models. Updates related logic in carcontroller, interface, and controlsd to accommodate this new lateral control method. Adjusts torque parameters for enhanced control in supported models.
2025-05-25 17:31:21 +02:00
DevTekVE d9f4ce82e6 clean 2025-05-25 17:31:21 +02:00
DevTekVE 648a1845d8 cleanup the mess 2025-05-25 17:31:21 +02:00
DevTekVE a87eff6d1c Add HKG Angle Live Tuning parameter and update related handling 2025-05-25 17:31:21 +02:00
DevTekVE dd6ad37e23 Absolutely zero clue on this, I did it with AI and it's for me to play. Don't take this notebook seriously please 2025-05-25 17:31:21 +02:00
DevTekVE c5e778b939 How annoying the linter on a comment lol 2025-05-25 17:31:21 +02:00
DevTekVE a9ab81a77a useless but should keep linter happy 2025-05-25 17:31:21 +02:00
DevTekVE 2d40e1d8e5 Refactor torque parameter handling in Hyundai carcontroller
Replaced direct access to `params` with instance variables for torque parameters to improve code clarity and maintainability. Updated smoothing factor description in angle tuning settings to include speed-related behavior. This enhances readability and prepares for further tuning adjustments.
2025-05-25 17:31:20 +02:00
DevTekVE 7c8f367a5d Fix data type for HkgTuningOverridingCycles value
Updated the value of HkgTuningOverridingCycles to a string for consistency with other parameters in the tuning configuration. This ensures proper handling and avoids potential issues with type mismatches.

Add overriding cycles parameter for torque adjustment

Introduced "HkgTuningOverridingCycles" for configurable user override torque ramp-down cycles. Updated relevant logic in torque control and UI settings to handle the new parameter. This improves flexibility in adjusting steering torque override behavior.
2025-05-25 17:31:20 +02:00
DevTekVE ff4cf558aa Add HKG angle tuning settings with min/max torque parameters
Introduce separate angle tuning controls for HKG vehicles, including smoothing factor, min torque, and max torque parameters. Refactor developer panel to integrate the new settings into a dedicated UI panel, enhancing modularity and customization capabilities.
2025-05-25 17:31:20 +02:00
DevTekVE 0e151e51bc Update HKG Angle Smoothing Factor description in Developer Panel
Enhanced the description to clarify its effect on steering behavior. Included details on how the smoothing factor impacts steering smoothness using EMA, aiding user understanding.
2025-05-25 17:31:20 +02:00
DevTekVE 60cc0031b0 Revert "Revert "Revert the EMA calculation on the curvature to test another approach""
This reverts commit 58fcda8c
2025-05-25 17:31:20 +02:00
DevTekVE d24cac0998 Refactor steering angle logic for smoother control adjustments
Refactored the calculation and application of the steering angle to improve code clarity and ensure smoother transitions. Removed unused parameter update logic in `latcontrol_angle.py` and enhanced handling of driver overrides in `carcontroller.py`.
2025-05-25 17:31:20 +02:00
DevTekVE 45d110830c Fix typo in parameter access method.
Replaced `self._params` with `self.params` to correctly access the parameter `HkgTuningAngleSmoothingFactor`. This ensures the smoothing factor is updated as intended during the control loop.
2025-05-25 17:31:20 +02:00
DevTekVE ea3a9ae911 Improve angle smoothing by integrating dynamic parameter tuning
Introduced a dynamic smoothing factor using the `HkgTuningAngleSmoothingFactor` parameter. This allows more granular control over curvature smoothing based on customizable user input, enhancing driving smoothness. Added necessary logic to process and apply this parameter efficiently.
2025-05-25 17:31:19 +02:00
DevTekVE 6bff8c0e7c Revert "Revert the EMA calculation on the curvature to test another approach"
This reverts commit bd471b3498.
2025-05-25 17:31:19 +02:00
DevTekVE bc6b8802b8 Add HKG angle smoothing factor for steering adjustments
Introduced a new parameter, `HkgTuningAngleSmoothingFactor`, to apply exponential moving average (EMA) smoothing to steering angle changes, reducing sudden adjustments. Added associated UI controls, parameter persistence, and integration into Hyundai carcontroller logic for improved steering stability.
2025-05-25 17:31:19 +02:00
DevTekVE 252ef572d3 Revert the EMA calculation on the curvature to test another approach 2025-05-25 17:31:19 +02:00
DevTekVE 414d397e3f Handle missing pygame import gracefully
Wrap the pygame import in a try-except block to catch ImportError. This prevents the script from crashing and provides a clear message prompting the user to install pygame if it's missing.

Remove "inputs" package and update "pygame" dependency

The "inputs" package has been removed from the lockfile and dependency list, while "pygame" is now included universally without the "dev" extra marker. This change simplifies dependencies and ensures consistency across environments.

Update dependencies: replace 'inputs' with 'pygame'

Replaced the 'inputs' library with 'pygame' for joystickd dependencies in `pyproject.toml`. Additionally, removed a redundant 'pygame' entry from the general dependencies.

Ugly, I know, but soundd is unhappy with joystick

Allowing lat with mads

Invert steering input for joystick control

The steering axis input is now multiplied by -1 to reverse its direction. This ensures correct handling of the left stick's horizontal input, aligning behavior with expected control dynamics.

Refactor joystick control to use pygame for broader support

Replaced the `inputs` library with `pygame` for joystick handling, providing improved compatibility with Xbox and PlayStation controllers. Added initialization, adaptive mappings, deadzone handling, and enhanced event processing for robust joystick operation. Updated README with dependencies and usage information for Xbox controllers.
2025-05-25 17:31:19 +02:00
DevTekVE 11b7b3789d Adjust speed thresholds in filter_speed_matrox.
Updated the `filter_speed_matrox` values to improve curvature filtering behavior at different speeds. This change ensures better handling and stability across a wider range of driving conditions.
2025-05-25 17:31:19 +02:00
DevTekVE 871ac53717 Optimize curvature filtering by adding speed-dependent logic.
Introduced speed-based dynamic alpha adjustment using interpolation for smoother curvature filtering. This improves steering angle calculations by adapting filter sensitivity to vehicle speed, enhancing control performance.
2025-05-25 17:31:19 +02:00
DevTekVE 64ea66b6e6 chsnge alpha to nicer value 2025-05-25 17:31:19 +02:00
DevTekVE 6d7c6759b3 Adjust curvature handling and filtering parameters
Updated curvature breakpoints and torque scaling for improved control in sharp turns. Increased filter alpha for faster curvature response while maintaining system stability.
2025-05-25 17:31:18 +02:00
DevTekVE 4cea013570 Adjust curvature handling and filtering parameters
Updated curvature breakpoints in Hyundai carcontroller to improve torque scaling for curved driving. Slightly refined the filter coefficient in lateral control for smoother curvature filtering and more accurate steering adjustments.
2025-05-25 17:31:18 +02:00
DevTekVE eb375c0587 Refactor curvature-based steering angle and torque logic.
Introduced dynamic torque scaling based on curvature for smoother and more adaptive steering control. Replaced raw curvature inputs with filtered curvature for enhanced stability and reduced noise in steering angle calculations. Removed unused speed scaling logic to simplify the lateral control flow.
2025-05-25 17:31:18 +02:00
DevTekVE 7fd8a5a4bd Reapply "Significant improvement on the jerkiness"
This reverts commit 85ce84e7b7.
2025-05-25 17:31:18 +02:00
DevTekVE b3c90216bb Revert "Significant improvement on the jerkiness"
This reverts commit ea1af879ba2905b076ccfe65993a9db701d689dd.

Revert "More improvement but still not quite"

This reverts commit ad95493c5c61b2ace7c459d2ebc151ddaa80040f.

Revert "Adjust low-speed scaling for lateral control angle"

This reverts commit 6f789ac1ebb66b0239b4028303573c2d7d386b39.

Revert "Refactor speed-based steering scaling logic."

This reverts commit 1d40735ab8db8d470ff3b287a6b42847beffff7d.
2025-05-25 17:31:18 +02:00
DevTekVE 10f345f956 Refactor speed-based steering scaling logic.
Updated the steering angle computation to use a clearer and more descriptive speed-scaling configuration. Replaced low-speed-specific logic with a generalized approach based on speed breakpoints and corresponding influence factors. This improves maintainability and ensures smoother steering adjustments at varying speeds.
2025-05-25 17:31:18 +02:00
DevTekVE 956d2c36d0 Adjust low-speed scaling for lateral control angle
Refined the low-speed scaling parameters by modifying speed breakpoints and factors. This improves handling at lower speeds for smoother and more predictable behavior.
2025-05-25 17:31:18 +02:00
DevTekVE 55e688b6f2 More improvement but still not quite 2025-05-25 17:31:17 +02:00
DevTekVE f017954027 Significant improvement on the jerkiness 2025-05-25 17:31:17 +02:00
DevTekVE 7e992d11b1 bump panda and opendbc 2025-05-25 17:31:15 +02:00
25 changed files with 3236 additions and 214 deletions
+1
View File
@@ -2,5 +2,6 @@ Wen
REGIST
PullRequest
cancelled
indeces
FOF
NoO
+258 -36
View File
@@ -10,13 +10,18 @@ on:
options:
- small
- big
- dm
workflow_call:
inputs:
target:
description: 'Model target to build (small or big)'
description: 'Model target to build (small, big, or dm)'
required: true
type: string
concurrency:
group: build-default-models-${{ inputs.target }}
cancel-in-progress: false
env:
HF_REPO: sunnypilot/sunnypilot_models_v1
@@ -28,9 +33,7 @@ jobs:
onnx_ref: ${{ steps.resolve.outputs.onnx_ref }}
onnx_path: ${{ steps.resolve.outputs.onnx_path }}
hf_defaults_path: ${{ steps.resolve.outputs.hf_defaults_path }}
target_hardware: ${{ steps.resolve.outputs.target_hardware }}
tinygrad_ref: ${{ steps.resolve.outputs.tinygrad_ref }}
dm_onnx_ref: ${{ steps.resolve.outputs.dm_onnx_ref }}
steps:
- uses: actions/checkout@v4
with:
@@ -44,12 +47,14 @@ jobs:
NAME=$(python3 -c "from openpilot.sunnypilot.models.model_name import DEFAULT_BIG_MODEL; print(DEFAULT_BIG_MODEL)")
ONNX_PATH="openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx"
HF_DEFAULTS_PATH="models/defaults/big"
TARGET_HW="usbgpu"
elif [ "${{ inputs.target }}" = "dm" ]; then
ONNX_PATH="openpilot/selfdrive/modeld/models/dmonitoring_model.onnx"
HF_DEFAULTS_PATH="models/defaults/dm"
NAME="dmonitoring_model ($(git log -1 --format=%cd --date=format:'%B %d, %Y' -- "$ONNX_PATH"))"
else
NAME=$(python3 -c "from openpilot.sunnypilot.models.model_name import DEFAULT_MODEL; print(DEFAULT_MODEL)")
ONNX_PATH="openpilot/selfdrive/modeld/models/driving_supercombo.onnx"
HF_DEFAULTS_PATH="models/defaults/small"
TARGET_HW="qcom"
fi
ONNX_REF=$(git log -1 --format='%H' -- "$ONNX_PATH")
@@ -59,65 +64,279 @@ jobs:
exit 1
fi
DM_ONNX_REF=""
if [ "${{ inputs.target }}" = "small" ]; then
DM_ONNX_REF=$(git log -1 --format='%H' -- openpilot/selfdrive/modeld/models/dmonitoring_model.onnx)
fi
echo "model_name=${NAME}" >> $GITHUB_OUTPUT
echo "onnx_ref=${ONNX_REF}" >> $GITHUB_OUTPUT
echo "onnx_path=${ONNX_PATH}" >> $GITHUB_OUTPUT
echo "hf_defaults_path=${HF_DEFAULTS_PATH}" >> $GITHUB_OUTPUT
echo "target_hardware=${TARGET_HW}" >> $GITHUB_OUTPUT
echo "tinygrad_ref=${TINYGRAD_REF}" >> $GITHUB_OUTPUT
echo "dm_onnx_ref=${DM_ONNX_REF}" >> $GITHUB_OUTPUT
build_driving_model:
build_small_model:
needs: resolve
uses: ./.github/workflows/sunnypilot-build-model.yaml
with:
upstream_branch: ${{ needs.resolve.outputs.onnx_ref }}
custom_name: ${{ needs.resolve.outputs.model_name }}
target_hardware: ${{ needs.resolve.outputs.target_hardware }}
secrets: inherit
if: ${{ inputs.target == 'small' }}
runs-on: [self-hosted, tici]
env:
SMALL_ONNX: openpilot/selfdrive/modeld/models/driving_supercombo.onnx
SMALL_PKL: openpilot/selfdrive/modeld/models/driving_tinygrad.pkl
steps:
- uses: actions/checkout@v4
with:
submodules: recursive
- name: Pull ONNX via LFS
run: git lfs pull -I "${{ env.SMALL_ONNX }}"
- name: Set environment variables
run: |
source /etc/profile
export UV_PROJECT_ENVIRONMENT=${HOME}/venv
export UV_PYTHON_PREFERENCE=managed
export UV_PYTHON_INSTALL_DIR=${HOME}/uv/python
export VIRTUAL_ENV=$UV_PROJECT_ENVIRONMENT
uv sync --frozen
printenv >> $GITHUB_ENV
- name: Disable powersave
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --disable
- name: Compile small model with stock compiler
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH="${PYTHONPATH}:${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}"
MODEL_SIZE=$(python3 -c "from openpilot.common.transformations.model import MEDMODEL_INPUT_SIZE as s; print(f'{s[0]}x{s[1]}')")
CAMERA_RES=$(python3 -c "from openpilot.common.transformations.camera import _ar_ox_fisheye as a, _os_fisheye as o; print(f'{a.width}x{a.height} {o.width}x{o.height}')")
FRAME_SKIP=$(python3 -c "from openpilot.selfdrive.modeld.constants import ModelConstants as MC; print(MC.MODEL_RUN_FREQ // MC.MODEL_CONTEXT_FREQ)")
TG_FLAGS="DEV=QCOM IMAGE=1 FLOAT16=1 NOLOCALS=1 JIT_BATCH_SIZE=0 OPENPILOT_HACKS=1"
env ${TG_FLAGS} python3 \
${{ github.workspace }}/openpilot/selfdrive/modeld/compile_modeld.py \
--onnx ${{ github.workspace }}/${{ env.SMALL_ONNX }} \
--model-size $MODEL_SIZE \
--camera-resolutions $CAMERA_RES \
--frame-skip $FRAME_SKIP \
--output ${{ github.workspace }}/${{ env.SMALL_PKL }}
- name: Chunk small pkl
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH=${{ github.workspace }}
python3 -c "
from openpilot.common.file_chunker import chunk_file, get_chunk_targets
import os
pkl = '${{ github.workspace }}/${{ env.SMALL_PKL }}'
size = os.path.getsize(pkl)
targets = get_chunk_targets(pkl, size)
chunk_file(pkl, targets)
print(f'Chunked into {len(targets)} files')
"
- name: Prepare output
env:
MODEL_NAME: ${{ needs.resolve.outputs.model_name }}
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH=${{ github.workspace }}
MODELS_DIR="${{ github.workspace }}/openpilot/selfdrive/modeld/models"
OUTPUT_DIR="${{ github.workspace }}/small_output"
PKL_BASE="driving_tinygrad.pkl"
mkdir -p "$OUTPUT_DIR"
cp "$MODELS_DIR/${PKL_BASE}".chunk* "$OUTPUT_DIR/"
cp "$MODELS_DIR/${PKL_BASE}.chunkmanifest" "$OUTPUT_DIR/"
python3 "${{ github.workspace }}/release/ci/model_generator.py" \
--model-dir "$MODELS_DIR" \
--output-dir "$OUTPUT_DIR" \
--custom-name "$MODEL_NAME" \
--upstream-branch "${{ needs.resolve.outputs.onnx_ref }}"
echo "model-${MODEL_NAME}-${{ github.run_number }}" > "$OUTPUT_DIR/artifact_name.txt"
- name: Upload small model artifact
uses: actions/upload-artifact@v4
with:
name: model-${{ needs.resolve.outputs.model_name }}-${{ github.run_number }}
path: ${{ github.workspace }}/small_output/
- name: Upload artifact name file
uses: actions/upload-artifact@v4
with:
name: artifact-name-${{ needs.resolve.outputs.model_name }}
path: ${{ github.workspace }}/small_output/artifact_name.txt
- name: Re-enable powersave
if: always()
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --enable
build_big_model:
needs: resolve
if: ${{ inputs.target == 'big' }}
runs-on: [self-hosted, usbgpu]
env:
BIG_ONNX: openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx
BIG_PKL: openpilot/selfdrive/modeld/models/big_driving_tinygrad.pkl
steps:
- uses: actions/checkout@v4
with:
submodules: recursive
- name: Pull big ONNX via LFS
run: git lfs pull -I "${{ env.BIG_ONNX }}"
- name: Set environment variables
run: |
source /etc/profile
export UV_PROJECT_ENVIRONMENT=${HOME}/venv
export UV_PYTHON_PREFERENCE=managed
export UV_PYTHON_INSTALL_DIR=${HOME}/uv/python
export VIRTUAL_ENV=$UV_PROJECT_ENVIRONMENT
uv sync --frozen
printenv >> $GITHUB_ENV
- name: Disable powersave
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --disable
- name: Wait for chestnut PCIe link
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH="${PYTHONPATH}:${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}"
python3 -c "
import time
from openpilot.system.hardware.chestnut.flash import link_up
for i in range(10):
if link_up():
print(f'PCIe link up after {i+1} attempt(s)')
break
time.sleep(1)
else:
raise RuntimeError('Chestnut PCIe link not ready after 10 attempts')
"
- name: Compile big model with stock compiler
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH="${PYTHONPATH}:${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}"
MODEL_SIZE=$(python3 -c "from openpilot.common.transformations.model import MEDMODEL_INPUT_SIZE as s; print(f'{s[0]}x{s[1]}')")
CAMERA_RES=$(python3 -c "from openpilot.common.transformations.camera import _ar_ox_fisheye as a, _os_fisheye as o; print(f'{a.width}x{a.height} {o.width}x{o.height}')")
FRAME_SKIP=$(python3 -c "from openpilot.selfdrive.modeld.constants import ModelConstants as MC; print(MC.MODEL_RUN_FREQ // MC.MODEL_CONTEXT_FREQ)")
TG_FLAGS="DEBUG=2 DEV=USB+AMD:LLVM WARP_DEV=QCOM FLOAT16=1 JIT_BATCH_SIZE=0 GMMU=0 TC_OPT=2"
env ${TG_FLAGS} python3 \
${{ github.workspace }}/openpilot/selfdrive/modeld/compile_modeld.py \
--onnx ${{ github.workspace }}/${{ env.BIG_ONNX }} \
--model-size $MODEL_SIZE \
--camera-resolutions $CAMERA_RES \
--frame-skip $FRAME_SKIP \
--output ${{ github.workspace }}/${{ env.BIG_PKL }}
- name: Chunk big pkl
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH=${{ github.workspace }}
python3 -c "
from openpilot.common.file_chunker import chunk_file, get_chunk_targets
import os
pkl = '${{ github.workspace }}/${{ env.BIG_PKL }}'
size = os.path.getsize(pkl)
targets = get_chunk_targets(pkl, size)
chunk_file(pkl, targets)
print(f'Chunked into {len(targets)} files')
"
- name: Prepare output
env:
MODEL_NAME: ${{ needs.resolve.outputs.model_name }}
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH=${{ github.workspace }}
MODELS_DIR="${{ github.workspace }}/openpilot/selfdrive/modeld/models"
OUTPUT_DIR="${{ github.workspace }}/big_output"
PKL_BASE="big_driving_tinygrad.pkl"
mkdir -p "$OUTPUT_DIR"
cp "$MODELS_DIR/${PKL_BASE}".chunk* "$OUTPUT_DIR/"
cp "$MODELS_DIR/${PKL_BASE}.chunkmanifest" "$OUTPUT_DIR/"
python3 "${{ github.workspace }}/release/ci/model_generator.py" \
--model-dir "$MODELS_DIR" \
--output-dir "$OUTPUT_DIR" \
--custom-name "$MODEL_NAME" \
--upstream-branch "${{ needs.resolve.outputs.onnx_ref }}"
echo "model-${MODEL_NAME}-${{ github.run_number }}" > "$OUTPUT_DIR/artifact_name.txt"
- name: Upload big model artifact
uses: actions/upload-artifact@v4
with:
name: model-${{ needs.resolve.outputs.model_name }}-${{ github.run_number }}
path: ${{ github.workspace }}/big_output/
- name: Upload artifact name file
uses: actions/upload-artifact@v4
with:
name: artifact-name-${{ needs.resolve.outputs.model_name }}
path: ${{ github.workspace }}/big_output/artifact_name.txt
- name: Re-enable powersave
if: always()
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --enable
upload_defaults:
needs: [ resolve, build_driving_model, build_dm_model ]
if: ${{ !cancelled() && needs.build_driving_model.result == 'success' && (inputs.target != 'small' || needs.build_dm_model.result == 'success') }}
needs: [ resolve, build_small_model, build_big_model, build_dm_model ]
if: |
${{
!cancelled() &&
(inputs.target == 'big' && needs.build_big_model.result == 'success' ||
inputs.target == 'small' && needs.build_small_model.result == 'success' ||
inputs.target == 'dm' && needs.build_dm_model.result == 'success')
}}
runs-on: ubuntu-24.04
permissions:
id-token: write
contents: write
env:
DM_ONNX: openpilot/selfdrive/modeld/models/dmonitoring_model.onnx
steps:
- uses: actions/checkout@v4
- name: Pull ONNX via LFS
run: git lfs pull -I "${{ needs.resolve.outputs.onnx_path }}${{ inputs.target == 'small' && ',openpilot/selfdrive/modeld/models/dmonitoring_model.onnx' || '' }}"
run: git lfs pull -I "${{ needs.resolve.outputs.onnx_path }}"
- name: Install huggingface_hub
run: pip install --upgrade "huggingface_hub>=0.22.0"
- name: Download driving artifact name
- name: Download artifact name
if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
uses: actions/download-artifact@v4
with:
name: artifact-name-${{ needs.resolve.outputs.model_name }}
path: artifact_name
- name: Read driving artifact name
- name: Read artifact name
if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
id: artifact
run: |
ARTIFACT_NAME=$(cat artifact_name/artifact_name.txt)
echo "artifact_name=$ARTIFACT_NAME" >> $GITHUB_OUTPUT
- name: Download driving model artifact
- name: Download model artifact
if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
uses: actions/download-artifact@v4
with:
name: ${{ steps.artifact.outputs.artifact_name }}
path: output
- name: Upload driving model to HF
- name: Upload model to HF
if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
env:
HF_OIDC_RESOURCE: datasets/${{ env.HF_REPO }}
ARTIFACT_NAME: ${{ steps.artifact.outputs.artifact_name }}
@@ -136,14 +355,14 @@ jobs:
--run-number "${{ github.run_number }}"
- name: Download DM artifact
if: ${{ inputs.target == 'small' }}
if: ${{ inputs.target == 'dm' }}
uses: actions/download-artifact@v4
with:
name: dm-model-${{ github.run_number }}
path: dm_output
- name: Generate DM metadata and upload to HF
if: ${{ inputs.target == 'small' }}
if: ${{ inputs.target == 'dm' }}
env:
HF_OIDC_RESOURCE: datasets/${{ env.HF_REPO }}
run: |
@@ -176,8 +395,8 @@ jobs:
metadata = {
'bundles': [{
'short_name': 'DMMODEL',
'display_name': 'dmonitoring_model',
'ref': '${{ needs.resolve.outputs.dm_onnx_ref }}',
'display_name': '${{ needs.resolve.outputs.model_name }}',
'ref': '${{ needs.resolve.outputs.onnx_ref }}',
'runner': 'tinygrad',
'build_time': datetime.now(UTC).strftime('%Y-%m-%dT%H:%M:%SZ'),
'models': [{
@@ -200,15 +419,15 @@ jobs:
--hf-defaults-path "${{ needs.resolve.outputs.hf_defaults_path }}" \
--artifact-name "dm-model-${{ github.run_number }}" \
--model-dir dm_output \
--onnx-path "${{ env.DM_ONNX }}" \
--onnx-ref "${{ needs.resolve.outputs.dm_onnx_ref }}" \
--model-name "dmonitoring_model" \
--onnx-path "${{ needs.resolve.outputs.onnx_path }}" \
--onnx-ref "${{ needs.resolve.outputs.onnx_ref }}" \
--model-name "${{ needs.resolve.outputs.model_name }}" \
--tinygrad-ref "${{ needs.resolve.outputs.tinygrad_ref }}" \
--run-number "${{ github.run_number }}"
build_dm_model:
needs: resolve
if: ${{ inputs.target == 'small' }}
if: ${{ inputs.target == 'dm' }}
runs-on: [self-hosted, tici]
env:
DM_ONNX: openpilot/selfdrive/modeld/models/dmonitoring_model.onnx
@@ -218,6 +437,9 @@ jobs:
with:
submodules: recursive
- name: Pull DM ONNX via LFS
run: git lfs pull -I "${{ env.DM_ONNX }}"
- name: Set environment variables
run: |
source /etc/profile
@@ -0,0 +1,66 @@
name: Download HF model chunks
description: Resolve and download model chunks from HuggingFace in parallel
inputs:
hf_repo:
description: HuggingFace dataset repo
required: true
models:
description: 'JSON array of {hf_path, onnx_hash, canonical} objects'
required: true
dest_dir:
description: Destination directory for downloaded chunks
required: true
runs:
using: composite
steps:
- name: Download model chunks
shell: bash
env:
HF_REPO: ${{ inputs.hf_repo }}
MODELS_JSON: ${{ inputs.models }}
DEST_DIR: ${{ inputs.dest_dir }}
run: |
set -eo pipefail
DOWNLOAD_LIST=$(mktemp)
resolve_chunks() {
local HF_PATH="$1" ONNX_HASH="$2" CANONICAL="$3" DEST_DIR="$4"
local JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_PATH}/default_models.json"
local DEFAULTS BUNDLE ARTIFACT BASE_URL NUM_CHUNKS
DEFAULTS=$(curl -fsSL "$JSON_URL")
BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)')
ARTIFACT=$(echo "$BUNDLE" | jq -r '.models[0].artifact')
BASE_URL=$(echo "$ARTIFACT" | jq -r '.download_uri.url' | sed 's|/[^/]*$||')
NUM_CHUNKS=$(echo "$ARTIFACT" | jq -r '.chunks | length')
mkdir -p "$DEST_DIR"
while IFS= read -r CHUNK_NAME; do
CHUNK_IDX=$(echo "$CHUNK_NAME" | grep -oP 'chunk\K[0-9]+of[0-9]+' || true)
if [ -z "$CHUNK_IDX" ]; then
echo "::error::Failed to parse chunk index from: $CHUNK_NAME"
return 1
fi
ENCODED_URL=$(python3 -c "import urllib.parse; print(urllib.parse.quote('${BASE_URL}/${CHUNK_NAME}', safe=':/'))")
printf '%s\t%s\n' "$ENCODED_URL" "${DEST_DIR}/${CANONICAL}.chunk${CHUNK_IDX}" >> "$DOWNLOAD_LIST"
done < <(echo "$ARTIFACT" | jq -r '.chunks[].file_name')
echo "$NUM_CHUNKS" > "${DEST_DIR}/${CANONICAL}.chunkmanifest"
}
echo "$MODELS_JSON" | jq -c '.[]' | while IFS= read -r model; do
HF_PATH=$(echo "$model" | jq -r '.hf_path')
ONNX_HASH=$(echo "$model" | jq -r '.onnx_hash')
CANONICAL=$(echo "$model" | jq -r '.canonical')
resolve_chunks "$HF_PATH" "$ONNX_HASH" "$CANONICAL" "$DEST_DIR"
done
TOTAL=$(wc -l < "$DOWNLOAD_LIST")
echo "Downloading $TOTAL chunks with 8 parallel connections..."
xargs -P8 -d'\n' -I{} bash -c '
URL="${1%% *}"
DEST="${1#* }"
echo "Downloading $(basename "$DEST")"
curl -fsSL --retry 3 --retry-delay 5 -o "$DEST" "$URL"
' _ {} < "$DOWNLOAD_LIST"
rm -f "$DOWNLOAD_LIST"
@@ -188,7 +188,7 @@ jobs:
if [ "${{ inputs.target_hardware }}" == "usbgpu" ]; then
echo "USBGPU build"
export USBGPU=1
TG_FLAGS="DEBUG=2 DEV=USB+AMD:LLVM WARP_DEV=QCOM FLOAT16=1 JIT_BATCH_SIZE=0 GMMU=0 TC_OPT=2"
TG_FLAGS="DEBUG=1 DEV=USB+AMD:LLVM WARP_DEV=QCOM FLOAT16=1 JIT_BATCH_SIZE=0 GMMU=0 TC_OPT=2"
OUTPUT_PKL="${{ env.MODELS_DIR }}/big_driving_tinygrad.pkl"
else
echo "QCOM build"
+243 -98
View File
@@ -39,6 +39,8 @@ jobs:
include_big_model: ${{ steps.strategy.outputs.include_big_model }}
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 1
- name: Extract deploy strategy
id: strategy
run: |
@@ -96,6 +98,8 @@ jobs:
}}
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 1
- name: Wait for Tests
uses: ./.github/workflows/wait-for-action # Path to where you place the action
with:
@@ -119,6 +123,7 @@ jobs:
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 1
submodules: recursive
ref: ${{ env.SOURCE_BRANCH }}
repository: ${{ github.event.pull_request.head.repo.fork && github.event.pull_request.head.repo.full_name || github.repository }}
@@ -165,7 +170,7 @@ jobs:
scons -j1 cache_dir="$SCONS_CACHE" --minimal \
openpilot/selfdrive/locationd openpilot/sunnypilot/selfdrive/locationd
echo "Building rest of sunnypilot"
/usr/bin/time -v scons -j$(nproc) cache_dir="$SCONS_CACHE" --minimal
SKIP_TINYGRAD_COMPILE=1 /usr/bin/time -v scons -j$(nproc) cache_dir="$SCONS_CACHE" --minimal
touch ${BUILD_DIR}/prebuilt
if [[ "${{ runner.debug }}" == "1" ]]; then
ls -la ${BUILD_DIR}
@@ -214,59 +219,174 @@ jobs:
outputs:
onnx_sha256: ${{ steps.resolve.outputs.onnx_sha256 }}
env:
GH_REPO: ${{ github.repository }}
HF_REPO: sunnypilot/sunnypilot_models_v1
HF_DEFAULTS_PATH: models/defaults/big
steps:
- uses: actions/checkout@v4
with:
ref: ${{ github.head_ref || github.ref_name }}
- run: git lfs pull -I "openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx"
- name: Check HF defaults and build if needed
- name: Resolve ONNX hash and tinygrad ref via API
id: resolve
run: |
ACTUAL_ONNX_HASH=$(sha256sum "openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx" | cut -d' ' -f1)
echo "Repo ONNX hash: $ACTUAL_ONNX_HASH"
echo "onnx_sha256=$ACTUAL_ONNX_HASH" >> $GITHUB_OUTPUT
REF="${{ github.head_ref || github.ref_name }}"
ONNX_HASH=$(gh api "repos/${GH_REPO}/contents/openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx?ref=${REF}" --jq '.content' | base64 -d | grep '^oid sha256:' | cut -d: -f2)
echo "ONNX hash: $ONNX_HASH"
echo "onnx_sha256=$ONNX_HASH" >> $GITHUB_OUTPUT
TINYGRAD_REF=$(gh api "repos/${GH_REPO}/contents/tinygrad_repo?ref=${REF}" --jq '.sha')
echo "tinygrad ref: $TINYGRAD_REF"
JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
check_hash() {
check_defaults() {
DEFAULTS=$(curl -fsSL "$JSON_URL" 2>/dev/null) || return 1
BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ACTUAL_ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
TINYGRAD_MATCH=$(echo "$DEFAULTS" | jq -r --arg ref "$TINYGRAD_REF" '.tinygrad_ref == $ref' 2>/dev/null)
[ "$TINYGRAD_MATCH" = "true" ] || return 1
BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
[ -n "$BUNDLE" ] && [ "$BUNDLE" != "null" ]
}
if check_hash; then
echo "HF defaults match repo ONNX"
else
echo "No matching model on HF — triggering build"
gh workflow run build-default-models.yaml --ref "${{ github.head_ref || github.ref_name }}" -f target=big
echo "Waiting for build to start..."
sleep 120
RUN_ID=$(gh run list --workflow=build-default-models.yaml --branch="${{ github.head_ref || github.ref_name }}" --limit=1 --json databaseId --jq '.[0].databaseId')
if [ -z "$RUN_ID" ] || [ "$RUN_ID" = "null" ]; then
echo "::error::Failed to find build-default-models run"
exit 1
fi
echo "Waiting for run $RUN_ID..."
gh run watch "$RUN_ID"
CONCLUSION=$(gh run view "$RUN_ID" --json conclusion --jq '.conclusion')
if [ "$CONCLUSION" != "success" ]; then
echo "::error::build-default-models failed: $CONCLUSION"
exit 1
fi
if ! check_hash; then
echo "::error::HF defaults still don't match after build"
exit 1
fi
if check_defaults; then
echo "HF defaults match repo ONNX hash and tinygrad ref"
exit 0
fi
echo "No matching model on HF — dispatching build"
gh workflow run build-default-models.yaml --ref "$REF" -f target=big
echo "Polling HF for big model availability..."
for i in $(seq 1 90); do
sleep 30
if check_defaults; then
echo "Big model available on HF after $((i * 30))s"
exit 0
fi
echo "Poll $i/90: not yet available"
done
echo "::error::Big model not available on HF after 45 minutes"
exit 1
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Cancel run on failure
if: failure()
run: gh run cancel ${{ github.run_id }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
prepare_small_model:
needs: [ prepare_strategy ]
runs-on: ubuntu-24.04
outputs:
driving_onnx_sha256: ${{ steps.resolve.outputs.driving_onnx_sha256 }}
env:
GH_REPO: ${{ github.repository }}
HF_REPO: sunnypilot/sunnypilot_models_v1
HF_DEFAULTS_PATH: models/defaults/small
steps:
- name: Resolve ONNX hash and tinygrad ref via API
id: resolve
run: |
REF="${{ github.head_ref || github.ref_name }}"
DRIVING_HASH=$(gh api "repos/${GH_REPO}/contents/openpilot/selfdrive/modeld/models/driving_supercombo.onnx?ref=${REF}" --jq '.content' | base64 -d | grep '^oid sha256:' | cut -d: -f2)
echo "Driving ONNX hash: $DRIVING_HASH"
echo "driving_onnx_sha256=$DRIVING_HASH" >> $GITHUB_OUTPUT
TINYGRAD_REF=$(gh api "repos/${GH_REPO}/contents/tinygrad_repo?ref=${REF}" --jq '.sha')
echo "tinygrad ref: $TINYGRAD_REF"
JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
check_defaults() {
DEFAULTS=$(curl -fsSL "$JSON_URL" 2>/dev/null) || return 1
TINYGRAD_MATCH=$(echo "$DEFAULTS" | jq -r --arg ref "$TINYGRAD_REF" '.tinygrad_ref == $ref' 2>/dev/null)
[ "$TINYGRAD_MATCH" = "true" ] || return 1
DRIVING=$(echo "$DEFAULTS" | jq --arg hash "$DRIVING_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
[ -n "$DRIVING" ] && [ "$DRIVING" != "null" ] || return 1
}
if check_defaults; then
echo "HF defaults match repo ONNX hash and tinygrad ref"
exit 0
fi
echo "No matching model on HF — dispatching build"
gh workflow run build-default-models.yaml --ref "$REF" -f target=small
echo "Polling HF for model availability..."
for i in $(seq 1 60); do
sleep 30
if check_defaults; then
echo "Model available on HF after $((i * 30))s"
exit 0
fi
echo "Poll $i/60: not yet available"
done
echo "::error::Small driving model not available on HF after 30 minutes"
exit 1
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Cancel run on failure
if: failure()
run: gh run cancel ${{ github.run_id }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
prepare_dm_model:
needs: [ prepare_strategy ]
runs-on: ubuntu-24.04
outputs:
dm_onnx_sha256: ${{ steps.resolve.outputs.dm_onnx_sha256 }}
env:
GH_REPO: ${{ github.repository }}
HF_REPO: sunnypilot/sunnypilot_models_v1
HF_DEFAULTS_PATH: models/defaults/dm
steps:
- name: Resolve ONNX hash and tinygrad ref via API
id: resolve
run: |
REF="${{ github.head_ref || github.ref_name }}"
DM_HASH=$(gh api "repos/${GH_REPO}/contents/openpilot/selfdrive/modeld/models/dmonitoring_model.onnx?ref=${REF}" --jq '.content' | base64 -d | grep '^oid sha256:' | cut -d: -f2)
echo "DM ONNX hash: $DM_HASH"
echo "dm_onnx_sha256=$DM_HASH" >> $GITHUB_OUTPUT
TINYGRAD_REF=$(gh api "repos/${GH_REPO}/contents/tinygrad_repo?ref=${REF}" --jq '.sha')
echo "tinygrad ref: $TINYGRAD_REF"
JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
check_defaults() {
DEFAULTS=$(curl -fsSL "$JSON_URL" 2>/dev/null) || return 1
TINYGRAD_MATCH=$(echo "$DEFAULTS" | jq -r --arg ref "$TINYGRAD_REF" '.tinygrad_ref == $ref' 2>/dev/null)
[ "$TINYGRAD_MATCH" = "true" ] || return 1
DM=$(echo "$DEFAULTS" | jq --arg hash "$DM_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
[ -n "$DM" ] && [ "$DM" != "null" ] || return 1
}
if check_defaults; then
echo "HF defaults match DM ONNX hash and tinygrad ref"
exit 0
fi
echo "No matching DM model on HF — dispatching build"
gh workflow run build-default-models.yaml --ref "$REF" -f target=dm
echo "Polling HF for DM model availability..."
for i in $(seq 1 60); do
sleep 30
if check_defaults; then
echo "DM model available on HF after $((i * 30))s"
exit 0
fi
echo "Poll $i/60: not yet available"
done
echo "::error::DM model not available on HF after 30 minutes"
exit 1
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -278,23 +398,24 @@ jobs:
publish:
concurrency:
# We do a bit of a hack here to avoid canceling the publishing job if a new commit comes in while we're publishing by adding the sha to the group name.
# This means that if multiple commits come in while we're publishing, they will be queued up and publish one after the other.
# Otherwise, if a job is waiting to be published due to environment wait time, it would be canceled by a new commit and restart the wait time.
group: ${{ needs.prepare_strategy.outputs.publish_concurrency_group }}
cancel-in-progress: ${{ needs.prepare_strategy.outputs.cancel_publish_in_progress == 'true' }}
if: ${{
always() && !cancelled() &&
needs.build.result == 'success' &&
needs.prepare_strategy.result == 'success' &&
needs.prepare_small_model.result == 'success' &&
needs.prepare_dm_model.result == 'success' &&
(!contains(github.event_name, 'pull_request') || (github.event.action == 'labeled' && github.event.label.name == 'prebuilt')) &&
(needs.prepare_strategy.outputs.include_big_model != 'true' || needs.prepare_chestnut.result == 'success')
}}
needs: [ build, prepare_strategy, prepare_chestnut ]
needs: [ build, prepare_strategy, prepare_chestnut, prepare_small_model, prepare_dm_model ]
runs-on: ubuntu-24.04
environment: ${{ needs.prepare_strategy.outputs.environment }}
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 1
- name: Download prebuilt artifact
uses: actions/download-artifact@v4
@@ -306,43 +427,16 @@ jobs:
mkdir -p ${{ env.OUTPUT_DIR }}
tar xzf prebuilt.tar.gz -C ${{ env.OUTPUT_DIR }}
- name: Prepare chestnut output
if: ${{ needs.prepare_chestnut.result == 'success' }}
run: |
mkdir -p "${{ github.workspace }}/chestnut_output"
tar xzf prebuilt.tar.gz -C "${{ github.workspace }}/chestnut_output"
- name: Download big model chunks from HF
if: ${{ needs.prepare_chestnut.result == 'success' }}
env:
HF_REPO: sunnypilot/sunnypilot_models_v1
HF_DEFAULTS_PATH: models/defaults/big
run: |
ONNX_HASH="${{ needs.prepare_chestnut.outputs.onnx_sha256 }}"
JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
DEFAULTS=$(curl -fsSL "$JSON_URL")
BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)')
mkdir -p big_model_chunks
ARTIFACT=$(echo "$BUNDLE" | jq -r '.models[0].artifact')
BASE_URL=$(echo "$ARTIFACT" | jq -r '.download_uri.url' | sed 's|/[^/]*$||')
NUM_CHUNKS=$(echo "$ARTIFACT" | jq -r '.chunks | length')
CANONICAL="big_driving_tinygrad.pkl"
echo "$ARTIFACT" | jq -r '.chunks[].file_name' | while read CHUNK_NAME; do
CHUNK_IDX=$(echo "$CHUNK_NAME" | grep -oP 'chunk\K[0-9]+of[0-9]+')
CANONICAL_CHUNK="${CANONICAL}.chunk${CHUNK_IDX}"
ENCODED_URL=$(python3 -c "import urllib.parse; print(urllib.parse.quote('${BASE_URL}/${CHUNK_NAME}', safe=':/'))")
echo "Downloading $CHUNK_NAME -> $CANONICAL_CHUNK"
curl -fsSL -o "big_model_chunks/${CANONICAL_CHUNK}" "$ENCODED_URL"
done
echo "$NUM_CHUNKS" > "big_model_chunks/${CANONICAL}.chunkmanifest"
- name: Inject big model into chestnut
if: ${{ needs.prepare_chestnut.result == 'success' }}
run: |
cp big_model_chunks/* "${{ github.workspace }}/chestnut_output/openpilot/selfdrive/modeld/models/"
- name: Download model chunks from HF
uses: ./.github/workflows/download-hf-model-chunks
with:
hf_repo: sunnypilot/sunnypilot_models_v1
dest_dir: ${{ env.OUTPUT_DIR }}/openpilot/selfdrive/modeld/models
models: |
[
{"hf_path": "models/defaults/small", "onnx_hash": "${{ needs.prepare_small_model.outputs.driving_onnx_sha256 }}", "canonical": "driving_tinygrad.pkl"},
{"hf_path": "models/defaults/dm", "onnx_hash": "${{ needs.prepare_dm_model.outputs.dm_onnx_sha256 }}", "canonical": "dmonitoring_model_tinygrad.pkl"}
]
- name: Configure Git
run: |
@@ -364,22 +458,6 @@ jobs:
"https://x-access-token:${{github.token}}@github.com/sunnypilot/sunnypilot.git" \
"${{ needs.prepare_strategy.outputs.extra_version_identifier }}"
- name: Publish chestnut branch
if: ${{ needs.prepare_chestnut.result == 'success' }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
CHESTNUT_BRANCH="${{ needs.prepare_strategy.outputs.new_branch }}-chestnut"
CHESTNUT_DIR="${{ github.workspace }}/chestnut_output"
${{ env.CI_DIR }}/publish.sh \
"${{ github.workspace }}" \
"$CHESTNUT_DIR" \
"$CHESTNUT_BRANCH" \
"${{ needs.prepare_strategy.outputs.version }}" \
"https://x-access-token:${{github.token}}@github.com/sunnypilot/sunnypilot.git" \
"${{ needs.prepare_strategy.outputs.extra_version_identifier }}"
- name: Tag ${{ needs.prepare_strategy.outputs.environment }}
if: ${{ needs.prepare_strategy.outputs.is_stable_branch == 'true' && (github.event_name != 'push' || !startsWith(github.ref, 'refs/tags/')) }}
run: |
@@ -387,12 +465,77 @@ jobs:
git tag -f -a ${TAG} -m "${{ needs.prepare_strategy.outputs.environment }} @ ${{ needs.prepare_strategy.outputs.version }} of build ${{ needs.prepare_strategy.outputs.build }}."
git push -f origin ${TAG}
publish_chestnut:
concurrency:
group: ${{ needs.prepare_strategy.outputs.publish_concurrency_group }}-chestnut
cancel-in-progress: ${{ needs.prepare_strategy.outputs.cancel_publish_in_progress == 'true' }}
if: ${{
always() && !cancelled() &&
needs.build.result == 'success' &&
needs.prepare_strategy.result == 'success' &&
needs.prepare_small_model.result == 'success' &&
needs.prepare_dm_model.result == 'success' &&
needs.prepare_chestnut.result == 'success' &&
(!contains(github.event_name, 'pull_request') || (github.event.action == 'labeled' && github.event.label.name == 'prebuilt'))
}}
needs: [ build, prepare_strategy, prepare_chestnut, prepare_small_model, prepare_dm_model ]
runs-on: ubuntu-24.04
environment: ${{ needs.prepare_strategy.outputs.environment }}
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 1
- name: Download prebuilt artifact
uses: actions/download-artifact@v4
with:
name: prebuilt
- name: Untar prebuilt
run: |
mkdir -p ${{ env.OUTPUT_DIR }}
tar xzf prebuilt.tar.gz -C ${{ env.OUTPUT_DIR }}
- name: Download model chunks from HF
uses: ./.github/workflows/download-hf-model-chunks
with:
hf_repo: sunnypilot/sunnypilot_models_v1
dest_dir: ${{ env.OUTPUT_DIR }}/openpilot/selfdrive/modeld/models
models: |
[
{"hf_path": "models/defaults/small", "onnx_hash": "${{ needs.prepare_small_model.outputs.driving_onnx_sha256 }}", "canonical": "driving_tinygrad.pkl"},
{"hf_path": "models/defaults/dm", "onnx_hash": "${{ needs.prepare_dm_model.outputs.dm_onnx_sha256 }}", "canonical": "dmonitoring_model_tinygrad.pkl"},
{"hf_path": "models/defaults/big", "onnx_hash": "${{ needs.prepare_chestnut.outputs.onnx_sha256 }}", "canonical": "big_driving_tinygrad.pkl"}
]
- name: Configure Git
run: |
git config --global user.email "github-actions[bot]@users.noreply.github.com"
git config --global user.name "github-actions[bot]"
- name: Publish chestnut branch
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
CHESTNUT_BRANCH="${{ needs.prepare_strategy.outputs.new_branch }}-chestnut"
${{ env.CI_DIR }}/publish.sh \
"${{ github.workspace }}" \
"${{ env.OUTPUT_DIR }}" \
"$CHESTNUT_BRANCH" \
"${{ needs.prepare_strategy.outputs.version }}" \
"https://x-access-token:${{github.token}}@github.com/sunnypilot/sunnypilot.git" \
"${{ needs.prepare_strategy.outputs.extra_version_identifier }}"
notify:
needs:
- prepare_strategy
- build
- publish
- publish_chestnut
- prepare_chestnut
- prepare_small_model
- prepare_dm_model
runs-on: ubuntu-24.04
if: ${{ (always() && !cancelled() && !failure())
&& needs.publish.result == 'success'
@@ -400,6 +543,8 @@ jobs:
&& (fromJSON(vars.DEV_FEEDBACK_NOTIFICATION_BRANCHES_V2)[github.head_ref || github.ref_name] != null) }}
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 1
- name: Prepare notification message
id: message
+7
View File
@@ -21,5 +21,12 @@
</clean>
</configuration>
</target>
<target id="f2590b2b-9b93-49f9-8510-da3f3724a2ae" name="replay" defaultType="TOOL">
<configuration id="d475264f-6f4c-4092-9b4e-6773309f38b7" name="replay" toolchainName="Default">
<build type="TOOL">
<tool actionId="Tool_External Tools_uv build tools replay" />
</build>
</configuration>
</target>
</component>
</project>
+7
View File
@@ -20,4 +20,11 @@
<option name="WORKING_DIRECTORY" value="$ProjectFileDir$" />
</exec>
</tool>
<tool name="uv build tools replay" showInMainMenu="false" showInEditor="false" showInProject="false" showInSearchPopup="false" disabled="false" useConsole="true" showConsoleOnStdOut="false" showConsoleOnStdErr="false" synchronizeAfterRun="true">
<exec>
<option name="COMMAND" value="bash" />
<option name="PARAMETERS" value="-c &quot;source .venv/bin/activate &amp;&amp; scons -u -j$(nproc) tools/replay/&quot;" />
<option name="WORKING_DIRECTORY" value="$ProjectFileDir$" />
</exec>
</tool>
</toolSet>
+1 -1
View File
@@ -1,5 +1,5 @@
<component name="ProjectRunConfigurationManager">
<configuration default="false" name="Build Debug" type="CLionExternalRunConfiguration" factoryName="Application" REDIRECT_INPUT="false" ELEVATE="false" USE_EXTERNAL_CONSOLE="false" EMULATE_TERMINAL="false" WORKING_DIR="file://$ProjectFileDir$/selfdrive/ui" PASS_PARENT_ENVS_2="true" PROJECT_NAME="sunnypilot" TARGET_NAME="uv Scons Build Debug" CONFIG_NAME="uv Scons Build Debug" RUN_PATH="ui">
<configuration default="false" name="Build Debug" type="CLionExternalRunConfiguration" factoryName="Application" REDIRECT_INPUT="false" ELEVATE="false" USE_EXTERNAL_CONSOLE="false" EMULATE_TERMINAL="false" WORKING_DIR="file://$ProjectFileDir$/selfdrive/ui" PASS_PARENT_ENVS_2="true" PROJECT_NAME="openpilot-special" TARGET_NAME="uv Scons Build Debug" CONFIG_NAME="uv Scons Build Debug" RUN_PATH="ui">
<envs>
<env name="QT_DBL_CLICK_DIST" value="150" />
</envs>
+27
View File
@@ -0,0 +1,27 @@
<component name="ProjectRunConfigurationManager">
<configuration default="false" name="Debug Route Controls" type="PythonConfigurationType" factoryName="Python">
<module name="openpilot-special" />
<option name="ENV_FILES" value="" />
<option name="INTERPRETER_OPTIONS" value="" />
<option name="PARENT_ENVS" value="true" />
<envs>
<env name="PYTHONUNBUFFERED" value="1" />
<env name="FINGERPRINT" value="KIA_EV9" />
<env name="SKIP_FW_QUERY" value="1" />
</envs>
<option name="SDK_HOME" value="" />
<option name="WORKING_DIRECTORY" value="$PROJECT_DIR$/selfdrive/car" />
<option name="IS_MODULE_SDK" value="true" />
<option name="ADD_CONTENT_ROOTS" value="true" />
<option name="ADD_SOURCE_ROOTS" value="true" />
<EXTENSION ID="PythonCoverageRunConfigurationExtension" runner="coverage.py" />
<option name="SCRIPT_NAME" value="$PROJECT_DIR$/selfdrive/car/card.py" />
<option name="PARAMETERS" value="" />
<option name="SHOW_COMMAND_LINE" value="false" />
<option name="EMULATE_TERMINAL" value="true" />
<option name="MODULE_MODE" value="false" />
<option name="REDIRECT_INPUT" value="false" />
<option name="INPUT_FILE" value="" />
<method v="2" />
</configuration>
</component>
+7
View File
@@ -0,0 +1,7 @@
<component name="ProjectRunConfigurationManager">
<configuration default="false" name="Replay for controls + ui" type="Multirun" separateTabs="false" reuseTabsWithFailures="false" startOneByOne="true" markFailedProcess="true" hideSuccessProcess="false" delayTime="0.0">
<runConfiguration name="replay for controls" type="Native Application" />
<runConfiguration name="Build Debug" type="Custom Build Application" />
<method v="2" />
</configuration>
</component>
+7
View File
@@ -0,0 +1,7 @@
<component name="ProjectRunConfigurationManager">
<configuration default="false" name="replay for controls" type="CLionNativeAppRunConfigurationType" focusToolWindowBeforeRun="true" PROGRAM_PARAMS="&quot;$Prompt$&quot; --block &quot;sendcan,carState,carParams,carOutput,liveTracks,carParamsSP,carStateSP,bookmarkButton&quot;" REDIRECT_INPUT="false" ELEVATE="false" USE_EXTERNAL_CONSOLE="false" EMULATE_TERMINAL="true" WORKING_DIR="file://$ProjectFileDir$/tools/replay" PASS_PARENT_ENVS_2="true" PROJECT_NAME="openpilot-special" TARGET_NAME="replay" CONFIG_NAME="replay" version="1" RUN_PATH="replay">
<method v="2">
<option name="CLION.COMPOUND.BUILD" enabled="true" />
</method>
</configuration>
</component>
+2
View File
@@ -196,6 +196,8 @@ inline static std::unordered_map<std::string, ParamKeyAttributes> keys = {
// Model Manager params
{"ModelManager_ActiveBundle", {PERSISTENT, JSON}},
{"ModelManager_ActiveJson", {CLEAR_ON_MANAGER_START, STRING}},
{"ModelManager_PrevBundle", {PERSISTENT, JSON}},
{"ModelManager_PrevBundle_USBGPU", {PERSISTENT, JSON}},
{"ModelManager_ClearCache", {CLEAR_ON_MANAGER_START, BOOL}},
{"ModelManager_DownloadIndex", {CLEAR_ON_MANAGER_START | CLEAR_ON_ONROAD_TRANSITION, INT}},
{"ModelManager_Favs", {PERSISTENT | BACKUP, STRING}},
+2
View File
@@ -37,6 +37,8 @@ SP_BRANCH_MIGRATIONS = {
("tizi", "release3-staging"): "release-tizi-staging",
("mici", "release3"): "release-mici",
("mici", "release3-staging"): "release-mici-staging",
("tici", "hkg-angle-steering-2025"): "hkg-angle-steering-2025-tici",
("tici", "hkg-angle-steering-2025-prebuilt"): "hkg-angle-steering-2025-tici-prebuilt"
}
BUILD_METADATA_FILENAME = "build.json"
+41 -39
View File
@@ -73,44 +73,45 @@ compile_modeld_script = [
model_w, model_h = MEDMODEL_INPUT_SIZE
frame_skip = ModelConstants.MODEL_RUN_FREQ // ModelConstants.MODEL_CONTEXT_FREQ
for usbgpu in [False, True] if USBGPU else [False]:
target_pkl_path = File(modeld_pkl_path(usbgpu)).abspath
# BIG_INTO_SMALL=1 builds the default target from the big model, e.g. to test it without a USB GPU
file_prefix, cmd_flags = ('big_', usbgpu_tg_flags) if usbgpu else ('big_' if os.getenv('BIG_INTO_SMALL') else '', tg_flags)
driving_onnx_deps = get_existing_chunks(File(f"models/{file_prefix}driving_supercombo.onnx").abspath)
camera_res_args = ' '.join(f'{cw}x{ch}' for cw, ch in CAMERA_CONFIGS)
# CPU 7 is isolated with isolcpus on AGNOS, so explicitly pin the compiler to it.
taskset = 'taskset -c 7 ' if arch == 'comma_arm64' else ''
cmd = (f'{cmd_flags} {mac_brew_string} {taskset}python3 {modeld_dir}/compile_modeld.py '
f'--model-size {model_w}x{model_h} '
f'--camera-resolutions {camera_res_args} '
f'--onnx {File(f"models/{file_prefix}driving_supercombo.onnx").abspath} '
f'--output {target_pkl_path} --frame-skip {frame_skip}')
onnx_sizes_sum = sum(os.path.getsize(f) for f in driving_onnx_deps)
chunk_targets = get_chunk_targets(target_pkl_path, estimate_pickle_max_size(onnx_sizes_sum))
def do_compile(target, source, env, command=cmd, pkl=target_pkl_path, chunks=chunk_targets):
from openpilot.system.hardware.chestnut.flash import link_up
# chestnut can enumerate before its PCIe link is up due to varying 12V power behavior across cars
for _ in range(10):
if link_up():
break
time.sleep(1)
else:
print("Chestnut not ready, skipping big model build")
return
if ret := env.Execute(command):
return ret
chunk_file(pkl, chunks)
def do_chunk(target, source, env, pkl=target_pkl_path, chunks=chunk_targets):
chunk_file(pkl, chunks)
actions = Action(do_compile, " [USBGPU] $TARGET") if usbgpu else [cmd, Action(do_chunk, " [CHUNK] $TARGET")]
node = lenv.Command(
chunk_targets,
tinygrad_files + compile_modeld_script + driving_onnx_deps + [Value(chunk_targets), chunker_file],
actions,
)
if usbgpu:
lenv.SideEffect(usbgpu_lock, node)
if not os.getenv('SKIP_TINYGRAD_COMPILE'):
for usbgpu in [False, True] if USBGPU else [False]:
target_pkl_path = File(modeld_pkl_path(usbgpu)).abspath
# BIG_INTO_SMALL=1 builds the default target from the big model, e.g. to test it without a USB GPU
file_prefix, cmd_flags = ('big_', usbgpu_tg_flags) if usbgpu else ('big_' if os.getenv('BIG_INTO_SMALL') else '', tg_flags)
driving_onnx_deps = get_existing_chunks(File(f"models/{file_prefix}driving_supercombo.onnx").abspath)
camera_res_args = ' '.join(f'{cw}x{ch}' for cw, ch in CAMERA_CONFIGS)
# CPU 7 is isolated with isolcpus on AGNOS, so explicitly pin the compiler to it.
taskset = 'taskset -c 7 ' if arch == 'comma_arm64' else ''
cmd = (f'{cmd_flags} {mac_brew_string} {taskset}python3 {modeld_dir}/compile_modeld.py '
f'--model-size {model_w}x{model_h} '
f'--camera-resolutions {camera_res_args} '
f'--onnx {File(f"models/{file_prefix}driving_supercombo.onnx").abspath} '
f'--output {target_pkl_path} --frame-skip {frame_skip}')
onnx_sizes_sum = sum(os.path.getsize(f) for f in driving_onnx_deps)
chunk_targets = get_chunk_targets(target_pkl_path, estimate_pickle_max_size(onnx_sizes_sum))
def do_compile(target, source, env, command=cmd, pkl=target_pkl_path, chunks=chunk_targets):
from openpilot.system.hardware.chestnut.flash import link_up
# chestnut can enumerate before its PCIe link is up due to varying 12V power behavior across cars
for _ in range(10):
if link_up():
break
time.sleep(1)
else:
print("Chestnut not ready, skipping big model build")
return
if ret := env.Execute(command):
return ret
chunk_file(pkl, chunks)
def do_chunk(target, source, env, pkl=target_pkl_path, chunks=chunk_targets):
chunk_file(pkl, chunks)
actions = Action(do_compile, " [USBGPU] $TARGET") if usbgpu else [cmd, Action(do_chunk, " [CHUNK] $TARGET")]
node = lenv.Command(
chunk_targets,
tinygrad_files + compile_modeld_script + driving_onnx_deps + [Value(chunk_targets), chunker_file],
actions,
)
if usbgpu:
lenv.SideEffect(usbgpu_lock, node)
# get model metadata
fn = File(f"models/dmonitoring_model").abspath
@@ -142,4 +143,5 @@ def tg_compile(flags, model_name):
Action(do_chunk, " [CHUNK] $TARGET")],
)
tg_compile(tg_flags, 'dmonitoring_model')
if not os.getenv('SKIP_TINYGRAD_COMPILE'):
tg_compile(tg_flags, 'dmonitoring_model')
@@ -115,8 +115,12 @@ class ModelsLayout(Widget):
def calculate_cache_size():
cache_size = 0.0
if os.path.exists(CUSTOM_MODEL_PATH):
cache_size = sum(os.path.getsize(os.path.join(CUSTOM_MODEL_PATH, file)) for file in os.listdir(CUSTOM_MODEL_PATH)) / (1024**2)
return cache_size
for file in os.listdir(CUSTOM_MODEL_PATH):
try:
cache_size += os.path.getsize(os.path.join(CUSTOM_MODEL_PATH, file))
except OSError:
continue
return cache_size / (1024**2)
def _clear_cache(self):
def _callback(response):
@@ -7,6 +7,7 @@ See the LICENSE.md file in the root directory for more details.
"""
import argparse
import math
import os
import tempfile
import time
@@ -66,14 +67,15 @@ def get_policy_npy_shapes(input_shapes: dict, is_supercombo: bool = False) -> tu
if desire_key:
shapes['desire'] = (input_shapes[desire_key][2],)
if is_supercombo and 'features_buffer' in input_shapes:
fb = input_shapes['features_buffer']
shapes['prev_feat'] = (fb[0], fb[2])
for key, shape in input_shapes.items():
if key not in (desire_key, 'features_buffer') and 'img' not in key:
shapes[key] = tuple(shape)
if is_supercombo and 'features_buffer' in input_shapes:
fb = input_shapes['features_buffer']
feat_dim = math.prod(fb[2:])
shapes['prev_feat'] = (fb[0], feat_dim)
sizes = [int(np.prod(size)) for size in shapes.values()]
return shapes, sizes
@@ -117,8 +119,9 @@ def generate_queues_and_npy(input_shapes: dict, frame_skip: int, device: str = D
}
if features_buffer:
feat_dim = math.prod(features_buffer[2:])
feat_q_len = frame_skip * features_buffer[1] if is_supercombo else frame_skip * (features_buffer[1] - 1) + 1
queues['feat_q'] = Tensor(np.zeros((feat_q_len, features_buffer[0], features_buffer[2]),
queues['feat_q'] = Tensor(np.zeros((feat_q_len, features_buffer[0], feat_dim),
dtype=np.float32), device=device).contiguous().realize()
queues.update({key: Tensor(value, device='NPY').realize() for key, value in npy_arrays.items() if key in ('tfm', 'big_tfm')})
@@ -183,14 +186,14 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
warped_dev = warped.to(Device.DEFAULT)
Tensor.realize(packed_npy_inputs_dev, warped_dev)
img = shift_and_sample(img_q, warped_dev[0:1], sample_skip_fn).realize()
big_img = shift_and_sample(big_img_q, warped_dev[1:2], sample_skip_fn).realize()
img = shift_and_sample(img_q, warped_dev[0:1], sample_skip_fn)
big_img = shift_and_sample(big_img_q, warped_dev[1:2], sample_skip_fn)
unpacked_tensors = [tensor.reshape(shape) for tensor, shape in zip(packed_npy_inputs_dev.split(npy_sizes), npy_shapes.values(), strict=True)]
unpacked_dict = dict(zip(npy_shapes.keys(), unpacked_tensors, strict=True))
desire_dev = unpacked_dict['desire']
desire_buf = shift_and_sample(desire_q, desire_dev.reshape(1, 1, -1), sample_desire_fn).realize()
desire_buf = shift_and_sample(desire_q, desire_dev.reshape(1, 1, -1), sample_desire_fn)
inputs = {desire_key: desire_buf}
for key, tensor_val in unpacked_dict.items():
@@ -199,7 +202,7 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
if 'prev_feat' in unpacked_dict:
prev_feat_dev = unpacked_dict['prev_feat']
inputs['features_buffer'] = shift_and_sample(feat_q, prev_feat_dev.reshape(1, 1, -1), sample_skip_fn).realize()
inputs['features_buffer'] = shift_and_sample(feat_q, prev_feat_dev.reshape(1, 1, -1), sample_skip_fn).reshape(input_shapes['features_buffer'])
if vision_runner:
vision_out_cast = next(iter(vision_runner({road_key: img, wide_key: big_img}).values())).cast('float32').realize()
@@ -211,7 +214,7 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
inputs.update({road_key: img, wide_key: big_img})
if 'features_buffer' not in inputs:
inputs['features_buffer'] = sample_skip_fn(feat_q)
inputs['features_buffer'] = sample_skip_fn(feat_q).reshape(input_shapes['features_buffer'])
policy_out = next(iter(policy_runners[0](inputs).values())).cast('float32').realize()
if 'features_buffer' not in inputs and features_slice is not None:
@@ -195,3 +195,85 @@ class TestReadFileChunkedToDisk(OpenpilotTestCase):
assert out.parent == Path(d)
assert out.read_bytes() == payload
class Test4DFeaturesBuffer(OpenpilotTestCase):
def test_get_policy_npy_shapes_4d(self):
from openpilot.sunnypilot.modeld_v2.compile_modeld import get_policy_npy_shapes
input_shapes = {
'desire_pulse': (1, 25, 8),
'features_buffer': (1, 24, 32, 512), # compare 4d to 3d for regression
'traffic_convention': (1, 2),
'action_t': (1, 2)
}
shapes, sizes = get_policy_npy_shapes(input_shapes, is_supercombo=True)
assert shapes['prev_feat'] == (1, 16384)
assert sizes == [8, 2, 2, 16384]
def test_get_policy_npy_shapes_3d(self):
from openpilot.sunnypilot.modeld_v2.compile_modeld import get_policy_npy_shapes
input_shapes = {
'desire_pulse': (1, 25, 8),
'features_buffer': (1, 24, 512),
'traffic_convention': (1, 2),
'action_t': (1, 2)
}
shapes, sizes = get_policy_npy_shapes(input_shapes, is_supercombo=True)
assert shapes['prev_feat'] == (1, 512)
assert sizes == [8, 2, 2, 512]
class TestStockCompileModeldEquivalence(OpenpilotTestCase):
def test_get_policy_npy_shapes_matches_stock(self):
from openpilot.selfdrive.modeld.compile_modeld import get_policy_npy_shapes as stock_get_policy_npy_shapes
from openpilot.sunnypilot.modeld_v2.compile_modeld import get_policy_npy_shapes as sunny_get_policy_npy_shapes
stock_input_shapes = {
'desire_pulse': (1, 25, 8),
'features_buffer': (1, 24, 512), # see below comment
'traffic_convention': (1, 2),
'action_t': (1, 2),
}
stock_shapes, stock_sizes = stock_get_policy_npy_shapes(stock_input_shapes)
sunny_shapes, sunny_sizes = sunny_get_policy_npy_shapes(stock_input_shapes, is_supercombo=True)
assert sunny_shapes == stock_shapes
assert sunny_sizes == stock_sizes
assert sunny_shapes['prev_feat'] == (1, 512)
def test_make_input_queues_full_stock_equivalence(self):
from openpilot.selfdrive.modeld.compile_modeld import make_input_queues as stock_make_input_queues
from openpilot.sunnypilot.modeld_v2.compile_modeld import make_supercombo_input_queues as sunny_make_supercombo_input_queues
input_shapes = {
'img': (1, 12, 128, 256),
'desire_pulse': (1, 25, 8),
'features_buffer': (1, 24, 512), # when https://github.com/commaai/openpilot/pull/38681 merges, update to 1,24,32,512
'traffic_convention': (1, 2),
'action_t': (1, 2),
}
frame_skip = 4
stock_queues, stock_npy = stock_make_input_queues(input_shapes, frame_skip, device='NPY')
sunny_queues, sunny_npy = sunny_make_supercombo_input_queues(input_shapes, frame_skip, device='NPY')
assert set(sunny_queues.keys()) == set(stock_queues.keys())
for key in stock_queues:
assert sunny_queues[key].shape == stock_queues[key].shape, \
f"Queue shape mismatch for {key}: sunny {sunny_queues[key].shape} != stock {stock_queues[key].shape}"
assert set(sunny_npy.keys()) == set(stock_npy.keys())
for key in stock_npy:
assert sunny_npy[key].shape == stock_npy[key].shape, \
f"Numpy array shape mismatch for {key}: sunny {sunny_npy[key].shape} != stock {stock_npy[key].shape}"
def test_make_warp_queues_stock_equivalence(self):
from openpilot.selfdrive.modeld.compile_modeld import make_warp_input_queues as stock_make_warp_queues
from openpilot.sunnypilot.modeld_v2.compile_modeld import make_warp_queues as sunny_make_warp_queues
stock_vision_shapes = {'img': (1, 12, 128, 256)} # for now?
stock_queues, stock_npy = stock_make_warp_queues(stock_vision_shapes, frame_skip=4, device='NPY')
sunny_queues, sunny_npy = sunny_make_warp_queues(device='NPY')
assert set(sunny_npy.keys()) == set(stock_npy.keys()) == {'tfm', 'big_tfm'}
for key in sunny_npy:
assert sunny_npy[key].shape == stock_npy[key].shape == (3, 3)
+2 -2
View File
@@ -138,8 +138,8 @@ class ModelCache:
class ModelFetcher:
"""Handles fetching and caching of model data from remote source"""
MODEL_URL = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_v20.json"
MODEL_URL_USBGPU = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_usbgpu_v21.json"
MODEL_URL = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_v21.json"
MODEL_URL_USBGPU = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_usbgpu_v22.json"
def __init__(self, params: Params):
self.params = params
+24 -19
View File
@@ -18,12 +18,11 @@ from openpilot.sunnypilot.models.constants import Meta, MetaSimPose, MetaTombRai
from openpilot.common.hardware.hw import Paths
# SET ME TO THE EXACT JSON VERSION WE SET IN SUNNYPILOT_MODELS REPO
REQUIRED_JSON_VERSION = 17
REQUIRED_JSON_VERSION = 18
CUSTOM_MODEL_PATH = Paths.model_root()
METADATA_PATH = Path(__file__).parent / '../models/supercombo_metadata.pkl'
ModelManager = custom.ModelManagerSP
_LAST_VALIDATED_RAW = None
def _compute_hash(file_path: str) -> str | None:
@@ -86,11 +85,11 @@ def _bundle_needs_reset(active_bundle: custom.ModelManagerSP.ModelBundle, availa
if available_bundles is not None:
matching_bundle = None
for bundle in available_bundles:
if getattr(active_bundle, 'ref', None) and getattr(bundle, 'ref', None):
if active_bundle.ref and bundle.ref:
if active_bundle.ref == bundle.ref:
matching_bundle = bundle
break
elif getattr(active_bundle, 'internalName', None) == getattr(bundle, 'internalName', None):
elif active_bundle.internalName == bundle.internalName:
matching_bundle = bundle
break
@@ -98,36 +97,42 @@ def _bundle_needs_reset(active_bundle: custom.ModelManagerSP.ModelBundle, availa
return True
if active_bundle.minimumSelectorVersion != matching_bundle.minimumSelectorVersion:
return True
active_runner = getattr(active_bundle, 'runner', None)
matching_runner = getattr(matching_bundle, 'runner', None)
if active_runner is not None and matching_runner is not None:
if getattr(active_runner, 'raw', active_runner) != getattr(matching_runner, 'raw', matching_runner):
return True
if active_bundle.runner.raw != matching_bundle.runner.raw:
return True
if set(_bundle_artifacts(active_bundle)) != set(_bundle_artifacts(matching_bundle)):
return True
return not _bundle_is_valid_locally(active_bundle)
# missing files trigger re-download, not selection reset
return False
def validate_active_bundle(params: Params, available_bundles: list[custom.ModelManagerSP.ModelBundle] | None = None) -> None:
global _LAST_VALIDATED_RAW
def _prev_bundle_key(is_usbgpu: bool) -> str:
return "ModelManager_PrevBundle_USBGPU" if is_usbgpu else "ModelManager_PrevBundle"
def validate_active_bundle(params: Params, available_bundles: list[custom.ModelManagerSP.ModelBundle] | None = None,
is_usbgpu: bool = False) -> None:
raw_bundle = params.get("ModelManager_ActiveBundle")
if not raw_bundle:
return
if raw_bundle == _LAST_VALIDATED_RAW:
prev = params.get(_prev_bundle_key(is_usbgpu))
if prev and (prev_bundle := get_active_bundle(params, raw_bundle_dict=prev)) is not None:
if not _bundle_needs_reset(prev_bundle, available_bundles):
params.put("ModelManager_ActiveBundle", prev, block=True)
return
active_bundle = get_active_bundle(params, raw_bundle_dict=raw_bundle)
if active_bundle is None or _bundle_needs_reset(active_bundle, available_bundles):
cloudlog.warning("Active model bundle invalid; resetting to default")
params.put(_prev_bundle_key(not is_usbgpu), raw_bundle, block=True)
prev = params.get(_prev_bundle_key(is_usbgpu))
if prev and (prev_bundle := get_active_bundle(params, raw_bundle_dict=prev)) is not None:
if not _bundle_needs_reset(prev_bundle, available_bundles):
params.put("ModelManager_ActiveBundle", prev, block=True)
return
params.remove("ModelManager_ActiveBundle")
params.put("ModelRunnerTypeCache", int(custom.ModelManagerSP.Runner.stock), block=True)
_LAST_VALIDATED_RAW = None
else:
_LAST_VALIDATED_RAW = raw_bundle
def get_active_bundle(params: Params | None = None, raw_bundle_dict: dict | bytes | None = None) -> "custom.ModelManagerSP.ModelBundle | None":
+8 -2
View File
@@ -257,15 +257,21 @@ class ModelManagerSP:
"""Main entry point for downloading a model bundle"""
asyncio.run(self._download_bundle(model_bundle, destination_path))
BOOT_SETTLE_TICKS = 10 # seconds at 1 Hz before validating active bundle
def main_thread(self) -> None:
"""Main thread for model management"""
rk = Ratekeeper(1, print_delay_threshold=None)
boot_ticks = 0
while True:
try:
self.sm.update(0)
self.available_models = self.model_fetcher.get_available_bundles(self.sm['deviceState'].chestnutPresent)
validate_active_bundle(self.params, self.available_models)
chestnut_present = self.sm['deviceState'].chestnutPresent
self.available_models = self.model_fetcher.get_available_bundles(chestnut_present)
if boot_ticks >= self.BOOT_SETTLE_TICKS:
validate_active_bundle(self.params, self.available_models, is_usbgpu=chestnut_present)
boot_ticks = min(boot_ticks + 1, self.BOOT_SETTLE_TICKS)
self.active_bundle = get_active_bundle(self.params)
if (index_to_download := self.params.get("ModelManager_DownloadIndex")) is not None:
+5 -2
View File
@@ -136,7 +136,7 @@ def generate_chunked_model(driving_pkl: Path) -> dict:
def create_metadata_json(models: list, output_dir: Path, custom_name=None, short_name=None, is_20hz=False, upstream_branch="unknown",
onnx_sha256=None) -> None:
onnx_sha256=None, is_big=False) -> None:
bundle_json = {
"short_name": short_name,
"display_name": custom_name or upstream_branch,
@@ -149,6 +149,7 @@ def create_metadata_json(models: list, output_dir: Path, custom_name=None, short
"generation": "-1",
"build_time": datetime.now(UTC).strftime("%Y-%m-%dT%H:%M:%SZ"),
"overrides": {},
"is_big": is_big,
"models": models,
}
@@ -186,6 +187,8 @@ if __name__ == "__main__":
print(f"No driving_tinygrad.pkl found in {_output_dir}", file=sys.stderr)
sys.exit(1)
is_big = _driving_pkl.name.startswith('big_')
if _pkl:
new_pkl = _output_dir / f"driving_{_pkl}_tinygrad.pkl"
if not new_pkl.exists():
@@ -196,4 +199,4 @@ if __name__ == "__main__":
_model_metadata = generate_chunked_model(_driving_pkl)
_onnx_sha256 = _hash_onnx_files(Path(args.model_dir))
create_metadata_json([_model_metadata], _output_dir, args.custom_name, _short_name, args.is_20hz, args.upstream_branch,
onnx_sha256=_onnx_sha256)
onnx_sha256=_onnx_sha256, is_big=is_big)
+1 -1
View File
@@ -47,7 +47,7 @@ git rm -rf $OUTPUT_DIR/.git || true # Doing cleanup, but it might fail if the .g
git remote remove origin || true # ensure cleanup
git remote add origin $GIT_ORIGIN
#git push origin -d $DEV_BRANCH || true # Ensuring we delete the remote branch if it exists as we are wiping it out
git fetch origin $DEV_BRANCH || (git checkout -b $DEV_BRANCH && git commit --allow-empty -m "sunnypilot v$VERSION release" && git push -u origin $DEV_BRANCH)
git fetch --depth 1 origin $DEV_BRANCH || (git checkout -b $DEV_BRANCH && git commit --allow-empty -m "sunnypilot v$VERSION release" && git push -u origin $DEV_BRANCH)
echo "[-] committing version $VERSION T=$SECONDS"
git add -f .
File diff suppressed because it is too large Load Diff
File diff suppressed because one or more lines are too long