mawei/openpilot-evo
1
0
Fork 0
mirror of https://github.com/infiniteCable2/openpilot.git synced 2026-09-27 18:13:41 +08:00
Code Issues Packages Projects Releases Wiki Activity
17,894 Commits 3 Branches 12 Tags
613d13bbfbc539b70ea442020ca2ce614a37e105
Commit Graph

736 Commits

Author SHA1 Message Date
Jason Wen 6979849305 Merge branch 'upstream/openpilot/master' into sync-20260414 
# Conflicts:
#	system/hardware/hardwared.py
 2026-04-14 12:22:13 -04:00
Harald Schäfer c91a0a83f6 Revert OP (#37812) 
* Revert "OP model 7 (#37760)"

This reverts commit 052692b25d.

* Revert "OP model (#37740)"

This reverts commit cb32793300.

* dead

* parse_model_outputs: drop extra space
 2026-04-12 23:47:43 -04:00
Jason Wen 9022b4d322 Revert "bump tg (#37700)" 
This reverts commit 55c38857
 2026-04-12 16:20:12 -04:00
Jason Wen b782958abd Revert "autodetect tg backend (#37778)" 
This reverts commit 21538e5a09.
 2026-04-12 16:20:03 -04:00
Jason Wen 3fa6726f88 Revert "autodetect tg backend: use CPU:LLVM on Linux (#37785)" 
This reverts commit 09a55a7833.
 2026-04-12 16:20:01 -04:00
Jason Wen 8c240cc1a4 Revert "Modeld: support uncompiled" 
This reverts commit 0a58d8b761.
 2026-04-12 16:19:59 -04:00
Jason Wen 9541692eb0 Merge branch 'upstream/openpilot/master' into sync-20260412 
# Conflicts:
#	cereal/log.capnp
#	docs/CARS.md
#	opendbc_repo
#	panda
#	selfdrive/modeld/SConscript
#	selfdrive/monitoring/test_monitoring.py
#	selfdrive/ui/soundd.py
#	tinygrad_repo
#	uv.lock
 2026-04-12 16:19:47 -04:00
Bruce Wayne 0a58d8b761 Modeld: support uncompiled 2026-04-10 19:28:41 -07:00
Harald Schäfer 09a55a7833 autodetect tg backend: use CPU:LLVM on Linux (#37785) 
autodetect tg backend: use CPU:LLVM on Linux, CPU on Darwin
 2026-04-08 16:16:39 -07:00
Harald Schäfer 21538e5a09 autodetect tg backend (#37778) 
* pick fastest

* save config

* fix

* Ignore generated tg_compiled_flags file

* helper

* cleaner

* whitespace not needed

* no shebang

* whitespace
 2026-04-08 13:55:00 -07:00
Kacper Rączy 08401a96c2 modeld: frame delay (#37731) 
* Frame delay

* Multiply

* If replay

* For long too

* DT_MDL / 2

* Shorten comment

* Just 50ms

* Remove REPLAY const
 2026-04-06 21:15:38 +00:00
Harald Schäfer 052692b25d OP model 7 (#37760) 
* a76ae294-e61a-43b8-b07e-c3496dbfc5ff/100

* recompile

* unused

* correct naming
 2026-04-03 09:34:03 -07:00
Jason Wen d398f9951e Merge branch 'upstream/openpilot/master' into sync-20260401 
# Conflicts:
#	.github/workflows/auto_pr_review.yaml
#	.github/workflows/repo-maintenance.yaml
#	README.md
#	SConstruct
#	docs/CARS.md
#	opendbc_repo
#	panda
#	selfdrive/car/card.py
#	selfdrive/controls/controlsd.py
#	selfdrive/selfdrived/selfdrived.py
#	selfdrive/test/process_replay/migration.py
#	selfdrive/ui/translations/app_fr.po
Platform List: sync with latest
Sync: `commaai/panda:master` → `sunnypilot/panda:master`
 2026-04-02 21:14:23 -04:00
Armand du Parc Locmaria 55c3885742 bump tg (#37700) 
* bump tg

* bump tg

* assign

* bump

* cpu llvm

* frame buffer updated in place, no need to return

* don't bake in stale pointers

* fix update image output indices

* lint

* bump
 2026-04-02 09:16:11 -07:00
Harald Schäfer cb32793300 OP model (#37740) 
* Off policy model

* 2f70b996-c604-4a46-9ac9-13ce7534605b/100

* misc fixes

* 1cc1791b-4555-41ce-a5cb-ce046967075a/100

* fix model

* 6ab6fae5-fbbd-4ad0-928a-b33794f60dba/100

* recomp

* update models

* qxfinally correct

* b8b96ac6-7918-401a-a862-eaf1fdbba88d/100

* wrong plan

* wrong plan

* Vf9b3fb5f-4d0d-4dcb-bc3a-5e94d1fdcdaa/200

* bump dbc

* ready to merge

* rename to on-policy

* Just cleanup big models for now

---------

Co-authored-by: Kacper Rączy <gfw.kra@gmail.com>
 2026-04-01 16:24:50 -07:00
ZwX1616 d8569b07eb DM: Lancia Delta HF Integrale model (#37696) 
* 00c00ac7-7b6e-4546-b86f-7ddd5f0596b4

* mici cleanup

* update msg

* rename
 2026-04-01 16:14:15 -07:00
Harald Schäfer 12f1be19cc POP model (#37727) 
* f9f6da19-c248-460f-8e16-d47e9824bfb7/100

* 05a58a51-e0e3-4e9b-8e27-e644685f2c50/100
 2026-03-24 14:40:45 -07:00
Jason Wen d5b25e14fd Merge branch 'upstream/openpilot/master' into sync-20260317 
# Conflicts:
#	.github/workflows/auto_pr_review.yaml
#	.gitignore
#	opendbc_repo
#	panda
#	selfdrive/ui/mici/layouts/home.py
#	selfdrive/ui/mici/layouts/onboarding.py
#	selfdrive/ui/mici/layouts/settings/device.py
#	selfdrive/ui/tests/diff/replay.py
#	selfdrive/ui/translations/app_fr.po
#	system/ui/mici_setup.py
Sync: `commaai/opendbc:master` → `sunnypilot/opendbc:master`
Sync: `commaai/panda:master` → `sunnypilot/panda:master`
 2026-03-17 23:02:10 -04:00
Shane Smiskol 6e7587a75c modeld: quiet do_chunk output during scons build (#37654) 
* modeld: quiet do_chunk output during scons build

SCons default-prints Python function actions with all their args.
The do_chunk function has 1259 tinygrad source files as deps, causing
a wall of text during builds. Wrap in SAction with a short strfunction.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* split compile and chunk into separate Commands

cleaner fix: do_chunk only depends on the pkl, not tinygrad files

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-11 23:35:56 -07:00
James Vecellio-Grant de0790f912 sunnypilot modeld: remove thneed modeld (#1731) 
* sunnypilot modeld: remove unused modeld

* more

---------

Co-authored-by: Jason Wen <haibin.wen3@gmail.com>
 2026-03-01 00:07:24 -05:00
Jason Wen d3e26cf695 Merge branch 'upstream/openpilot/master' into sync-20260227 
# Conflicts:
#	.github/workflows/release.yaml
#	.github/workflows/setup/action.yaml
#	.github/workflows/tests.yaml
#	panda
Sync: `commaai/opendbc:master` → `sunnypilot/opendbc:master`

Sync: `commaai/panda:master` → `sunnypilot/panda:master`
 2026-02-27 17:05:28 -05:00
Jason Wen 59a16b9cdc Merge branch 'upstream/openpilot/master' into sync-20260225 
# Conflicts:
#	.github/workflows/auto_pr_review.yaml
#	.github/workflows/badges.yaml
#	.github/workflows/mici_raylib_ui_preview.yaml
#	.github/workflows/prebuilt.yaml
#	.github/workflows/raylib_ui_preview.yaml
#	.github/workflows/release.yaml
#	.github/workflows/repo-maintenance.yaml
#	.github/workflows/tests.yaml
#	.gitignore
#	Dockerfile.openpilot_base
#	SConstruct
#	docs/CARS.md
#	opendbc_repo
#	panda
#	release/build_release.sh
#	selfdrive/modeld/SConscript
#	selfdrive/modeld/modeld.py
#	selfdrive/pandad/panda_safety.cc
#	selfdrive/pandad/pandad.cc
#	selfdrive/pandad/pandad.py
#	selfdrive/test/process_replay/process_replay.py
#	selfdrive/ui/layouts/onboarding.py
#	selfdrive/ui/mici/layouts/home.py
#	selfdrive/ui/tests/diff/replay.py
#	selfdrive/ui/tests/test_ui/raylib_screenshots.py
#	tools/mac_setup.sh
#	uv.lock
 2026-02-27 16:12:57 -05:00
ZwX1616 04dcdf46bc DM: Le Mans GT3 Model (#37425) 
* 81248b12-6592-4a5c-9b59-a44c64123b2b

* install tg instead of onnx

* fix python path

---------

Co-authored-by: Bruce Wayne <harald.the.engineer@gmail.com>
 2026-02-26 16:10:57 -08:00
Harald Schäfer 0b6da2077f parse planplus (#37386) 2026-02-24 15:41:00 -08:00
Harald Schäfer 159d3a30e3 RM onnx (#37377) 
* Give tf flags to onnx parse

* rm onnx again

* update lock
 2026-02-24 15:35:52 -08:00
Harald Schäfer c787507449 Revert "rm onnx (#37285)" (#37379) 
This reverts commit 23e1c4f49e.
 2026-02-24 09:43:47 -08:00
Harald Schäfer 16dda06a0c Reapply chunker (#37292) 
* Reapply chunker

* good size

* rm glob

* cleaner

* back to 45mb

* warp need not be fixed

* add manifest path

* lil cleaner
 2026-02-23 16:49:48 -08:00
Adeeb Shihadeh 23e1c4f49e rm onnx (#37285) 2026-02-20 16:47:47 -08:00
Bruce Wayne d6af0e6eb5 Revert "Simpler file chunker (#37276)" 
This reverts commit b27fa58444.
 2026-02-20 16:43:43 -08:00
Harald Schäfer b27fa58444 Simpler file chunker (#37276) 
* Chunk tinygrad pkl below GitHub max size

* pull that out

* rm glob

* make work

* Single name def

* unused comment

* more cleanups

* revert that

* 10MB overhead

---------

Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
 2026-02-20 10:37:14 -08:00
ZwX1616 3c4ddba992 DM: Ford GT Le Mans Model (#37257) 
* b483cec4-7816-4570-a774-be3a2c100098/50

* shipfest

* da4b8724-8998-45da-aa36-d8fb390492b9

* revert

* typo

* deprecates

* 53a2718f-206b-4400-a70b-16915de18472/200

* bump

* update
 2026-02-18 20:09:46 -08:00
James Vecellio-Grant a48988ccb3 chore: sync tinygrad (#1680) 
* chore: sync tinygrad

Runs great in sim. now we need to rebuild some models

* oops forgot to unblock this after testing

* helpers

* oh yeah

* latest tg

* this wont do anything empriically

* reduce complexity

* okay lint

* Update tinygrad_runner.py

* Update modeld.py

* Update build-all-tinygrad-models.yaml

* tinygrad bump

* Update modeld.py

* Update tinygrad_runner.py

* bump

* Update SConscript

* Update SConscript

* com

* Update fetcher.py

* Update helpers.py

* Update model_runner.py

* Update model_runner.py

---------

Co-authored-by: Jason Wen <haibin.wen3@gmail.com>
 2026-02-16 03:01:59 -05:00
Adeeb Shihadeh ced5f417b8 MetaDrive: slim down & enable CI test (#37216) 
* MetaDrive slimming

* enable

* lock

* modeld fix

* minimal
 2026-02-14 21:16:26 -08:00
YassineYousfi 2ba6df2506 chunk tinygrad pkl below GitHub max size - NoCache and AlwaysBuild (#37194) 
* nocache

* +

* fixes

* lint

* not split

* use pathlib

* cleanup

* better

* even better
 2026-02-13 10:14:24 -08:00
Harald Schäfer af1583cdfc Reapply tgwarp w NV12 fix (#37168) 
* Revert "Revert tgwarp again (#37161)"

This reverts commit 45099e7fcd.

* Weird uv sizes

* Fix interleaving

* Fix on CPU

* make CPU safe

* Prevent corruption without clone

* Claude knows speeed

* fix interleaving

* less kernels

* blob caching

* This is still slightly faster

* Comment for blob cache
 2026-02-12 08:59:19 -08:00
Jason Wen 52fb0b8171 Merge branch 'upstream/openpilot/master' into sync-20260211 
# Conflicts:
#	.github/workflows/auto_pr_review.yaml
#	.github/workflows/tests.yaml
#	opendbc_repo
#	panda
#	selfdrive/pandad/pandad.py
#	selfdrive/test/process_replay/test_processes.py
 2026-02-11 20:16:02 -05:00
Harald Schäfer 45099e7fcd Revert tgwarp again (#37161) 
* Reapply "revert tg calib and opencl cleanup (#37113)" (#37115)

This reverts commit 667f3bb32f.

* revert msgq too

* msgq on master
 2026-02-10 23:12:41 -08:00
ZwX1616 e946e9de0b Revert "DM: Ford GT model" (#37148) 
Revert "DM: Ford GT model (#37013)"

This reverts commit 1459d3519d.
 2026-02-10 13:56:07 -08:00
Harald Schäfer 3d11e8ef36 Revert "Chunk big model files (#37134)" (#37139) 
This reverts commit a941e8f78f.
 2026-02-09 20:58:22 -08:00
James Vecellio-Grant 73f720220b modeld: simplify model run processing (#37138) 
Hi! The point of this pr is to make the model run easier to read. On the latest tinygrad numpy().flatten() empirically does the same thing as the internal contiguous().realize().uop.base.buffer.numpy(). numpy() is also documented (docstrings), which can assist new contributors in learning what each potential execution does. Torq_boi or yassine, I know you want proof in the code base, so here it is. As of tinygrad commit 2f55005:

 in tinygrad_repo/tinygrad/tensor.py
Lines 316-318 (def _buffer): ensure the tenso is contiguous() and realized() before accessing the raw buffer.
Line 378 (def numpy): Wraps the buffer access and adds a reshape to match the tensor shape.
self._buffer() is what executes contiguous().realize() and returns the buffer object.
Calling numpy() on that buffer object returns a 1D array (defined in tinygrad/device.py:193 via np.frombuffer).
The reshape(self.shape) at the end of Tensor.numpy() then adds dimensions to that 1D array. The added .flatten() removes those dimensions, flattening it back to a 1D array. Effectively the same as what is currently done, but less complex.
 2026-02-09 20:24:25 -08:00
Harald Schäfer a941e8f78f Chunk big model files (#37134) 
* file chunking

* try this

* more cleanup

* cleaner
 2026-02-09 15:29:50 -08:00
Adeeb Shihadeh 667f3bb32f Revert "revert tg calib and opencl cleanup (#37113)" (#37115) 
* Revert "revert tg calib and opencl cleanup (#37113)"

This reverts commit 51312afd3d.

* power draw is a lil higher

* just don't miss a cycle

* fix warp targets

* fix tinygrad dep
 2026-02-07 21:36:44 -08:00
Harald Schäfer 51312afd3d revert tg calib and opencl cleanup (#37113) 
* Revert "Remove all the OpenCL (#37105)"

This reverts commit d5cbb89d84.

* Revert "rm common/mat.h"

This reverts commit 4ce701150a.

* Revert "Calibrate in tg (#36621)"

This reverts commit 593c3a0c8e.
 2026-02-07 09:10:29 -08:00
Adeeb Shihadeh d5cbb89d84 Remove all the OpenCL (#37105) 
* Remove all the OpenCL

* lil more

* bump msgq
 2026-02-06 16:36:47 -08:00
Harald Schäfer 593c3a0c8e Calibrate in tg (#36621) 
* squash

* bump tg

* fix linmt

* Ready to merge

* cleaner

* match modeld

* more dead stuff
 2026-02-06 14:13:46 -08:00
Jason Wen 959ebd22d8 Merge branch 'upstream/openpilot/master' into sync-20260201 
# Conflicts:
#	.github/workflows/auto_pr_review.yaml
#	.github/workflows/docs.yaml
#	.github/workflows/repo-maintenance.yaml
#	.gitignore
#	docs/CARS.md
#	opendbc_repo
#	panda
#	pyproject.toml
#	selfdrive/controls/lib/longitudinal_planner.py
#	selfdrive/test/process_replay/ref_commit
#	tinygrad_repo
 2026-02-04 00:14:58 -05:00
YassineYousfi 5b6436a90c CD210 model (#37050) 
a27b3122-733e-4a65-938b-acfebebbe5e8/100
 2026-02-03 19:14:02 -08:00
King Art db3df61c34 fix non-determinism in modeld build (#37042) 
* fix non-determinism in selfservice model build

also trim down model compile dependencies to the minimum required

* Apply suggestions from code review

---------

Co-authored-by: Shane Smiskol <shane@smiskol.com>
 2026-01-30 17:16:56 -08:00
ZwX1616 1459d3519d DM: Ford GT model (#37013) 
* b483cec4-7816-4570-a774-be3a2c100098/50

* shipfest

* da4b8724-8998-45da-aa36-d8fb390492b9

* revert

* typo

* deprecates
 2026-01-22 18:41:08 -08:00
Jason Wen 53327edb50 Merge branch 'upstream/openpilot/master' into sync-20260111 
# Conflicts:
#	common/api.py
#	docs/CARS.md
#	opendbc_repo
#	panda
#	scripts/lint/lint.sh
#	selfdrive/car/car_specific.py
#	selfdrive/car/card.py
#	selfdrive/test/process_replay/ref_commit
#	system/hardware/hardwared.py
#	tinygrad_repo
 2026-01-20 07:29:25 -05:00