8 Commits

Author	SHA1	Message	Date
discountchubbs	89e536f909	pkl name	2026-08-13 13:22:43 -07:00
Nayan	5bdc0c23a9	modeld_v2: Support Deep Models (#1887) ... * modeld_v2: safe model validation * fix string * numpy * dumb * god use full attribute names please * modeld_v2: refactor compile_modeld * redundant * CREAM AND SUGAR * gpu stuffs * Update fetcher.py * Update compile_modeld.py * Update compile_modeld.py * Update compile_modeld.py * Update compile_modeld.py * summary * Update compile_modeld.py * Update compile_modeld.py * Update compile_modeld.py * i could lie say * needed * i could * Update compile_modeld.py * done done done * bye metadata * simplify * deeeeep * oopsie * i don't know what i'm doing * it's a supercombo * wtf. ghostwriter * i might be blind * fuck. i AM blind. or dumb. or both. * hmmmm * read/open - what's the difference * realize. that i don't know shit * whatever * fix paths * fuckit. dynamic everything. * simplify everything. * fix macos cabana * np.random.seed is deprecated, use Generator or default rng instead @nayan * this is annoying me * too much fluff * no * lint be crazy now, man i've been away a while * back * fix pkl loader test * that comment was wrong, its still per model, just compiled at with the input/output shapes * fix chunking * dump and assign to cpu * prev_feat in cpu to prevent corruption * add todo-sp * desire me? * allow legacy * lint * shapey * bye --------- Co-authored-by: discountchubbs <alexgrant990@gmail.com> Co-authored-by: James Vecellio-Grant <159560811+Discountchubbs@users.noreply.github.com> Co-authored-by: Jason Wen <haibin.wen3@gmail.com>	2026-08-05 12:30:28 -07:00
Jason Wen	36a9c02b8f	sync: post-merge fixes for tinygrad bump	2026-06-03 14:56:32 -04:00
Jason Wen	b5d2026fc7	sunnypilot models: support for on-policy models	2026-04-02 21:14:39 -04:00
James Vecellio-Grant	b2201c2a1d	CI: validate model after build (#1744) ... Co-authored-by: Jason Wen <haibin.wen3@gmail.com>	2026-03-01 01:12:16 -05:00
James Vecellio-Grant	4d65c52e6d	modeld_v2: refactor abstract class to support off-policy models (#1672) ... * modeld_v2: refactor abstract class to support off-policy models. * whoops * bump	2026-02-05 08:35:57 -05:00
James Vecellio-Grant	6d41ce2032	ci: Refactor model building workflows (#1096) ... * Tinygrad bump from sync-20250627 * bump tinygrad_repo * Reformat metadata generator to match driving_models.json * bump tinygrad * Revert "bump tinygrad" This reverts commit f479dfd502. * revert me after SP model compiled * Model recompiled successfully, initiate "revert me after SP model compiled" This reverts commit 95706eb688. * The "FillMe" placeholder caused an extra 10 seconds of work * bump to 22Jul2025 * Update build-all-tinygrad-models.yaml * Update build-all-tinygrad-models.yaml * Update build-all-tinygrad-models.yaml * Update build-all-tinygrad-models.yaml * Update build-all-tinygrad-models.yaml * Update build-all-tinygrad-models.yaml * Update build-all-tinygrad-models.yaml * Allow more dynamic short names This should hopefully be future-proof for now.. It's robust enough to return the correct word-digit format (see example on how it generates from given display name below): 'Last Horizon V2 (November 22, 2024)' -> LHV2 'Alabama (November 25, 2024)' -> ALABAMA 'PlayStation (December 03, 2024)' -> PLAYSTAT 'Postal Service (December 09, 2024)' -> PS 'Null Pointer (December 13, 2024)' -> NP 'North America (December 16, 2024)' -> NA 'National Public Radio (December 18, 2024)' -> NPR 'Filet o Fish (March 7, 2025)' -> FOF 'Tomb Raider 2 (April 18, 2025)' -> TR2 'Tomb Raider 3 (April 22, 2025)' -> TR3 'Tomb Raider 4 (April 25, 2025)' -> TR4 'Tomb Raider 5 (April 25, 2025)' -> TR5 'Tomb Raider 6 (April 30, 2025)' -> TR6 'Tomb Raider 7 (May 07, 2025)' -> TR7 'Down to Ride (Revision: May 10, 2025)' -> DTR 'SP Vikander Model (May 16, 2025)' -> SPVM 'VFF Driving (May 15, 2025)' -> VFFD 'Secret Good Openpilot (May 16, 2025)' -> SGO 'Vegetarian Filet o Fish (May 29, 2025)' -> VFOF 'Down To Ride (Revision: May 30, 2025)' -> DTR 'Vegetarian Filet o Fish v2 (June 05, 2025)' -> VFOFV2 'Kerrygold Driving (June 08, 2025)' -> KD 'Tomb Raider 10 (June 16, 2025)' -> TR10 'Organic Kerrygold (June 17, 2025)' -> OK 'Liquid Crystal Driving (June 21, 2025)' -> LCD 'Vegetarian Filet o Fish v3 (June 21, 2025)' -> VFOFV3 'Vibe Model [Custom Model]' -> VMCM 'Tomb Raider 13 (June 27, 2025)' -> TR13 'Aggressive TR (June 28, 2025)' -> ATR 'Tomb Raider 14 (June 30, 2025)' -> TR14 'Cookiemonster Tomb Raider (July 02, 2025)' -> CTR 'Down to Ride (Revision: July 07, 2025)' -> DTR 'Simple Plan Driving (July 07, 2025)' -> SPD 'Down to Ride (Revision: July 08, 2025)' -> DTR 'Tomb Raider 15 (July 09, 2025)' -> TR15 'Tomb Raider 15 rev-2 (July 11, 2025)' -> TR15R2 'Le Tomb Raider 14 (July 14, 2025)' -> LTR14 'Le Tomb Raider 14h (July 17, 2025)' -> LTR14H 'Tomb Raider 16 (July 18, 2025)' -> TR16 'Tomb Raider 16v2 (July 21, 2025)' -> TR16V2 * Update build-all-tinygrad-models.yaml * Update build-all-tinygrad-models.yaml * No need to sleep 3 seconds, just send it * try dynamic * cleanup * Update build-single-tinygrad-model.yaml * bc devtekve said. also, this is repetitive af * Revert "bc devtekve said. also, this is repetitive af" This reverts commit 3a0c1562de. * maybe we could use a script instead that both build all That both build all and sunnypilot-build-model reference * refactor: consolidate model building steps into a single workflow * tweak * tweakx2 * tweakx3 * tweakx4 * dunno dunno... * output dir * lots of changes * Revert "lots of changes" This reverts commit 4aadb0ee29. * fail if all fail * no inputs needed * make it easier for us * note failure and exit 0 * Update build-all-tinygrad-models.yaml * not needed unless we really want it * Update build-single-tinygrad-model.yaml * Merge branch 'sync-20250627-tinygrad' of github.com:sunnypilot/sunnypilot into sync-20250627-tinygrad * retry for failed ? * always run this step because sometimes one build fails which causes the matrix to fail, but most builds still have uploaded artifacts. * strip * no escape * Update build-all-tinygrad-models.yaml * Test case from terminal run (openpilot) james@Mac sunnypilot % jq -c '[.bundles[] | select(.runner=="tinygrad") | {ref, display_name: (.display_name | gsub(" \\([^)]*\\)"; "")), is_20hz}]' \ /Users/james/Documents/GitHub/sunnypilot-docs/docs/driving_models_v6.json > matrix.json mkdir -p output touch "output/model-Tomb Raider 16v2 (July 21, 2025)-544" touch "output/model-Space Lab Model (July 24, 2025)-547" touch "output/model-Space Lab Model v1 (July 24, 2025)-548" built=(); while IFS= read -r line; do built+=("$line"); done < <( ls output | sed -E 's/^model-//' | sed -E 's/-[0-9]+$//' | sed -E 's/ \([^)]*\)//' | awk '{gsub(/^ +| +$/, ""); print}' ) jq -c --argjson built "$(printf '%s\n' "${built[@]}" | jq -R . | jq -s .)" \ 'map(select(.display_name as $n | ($built | index($n | gsub("^ +| +$"; "")) | not)))' \ matrix.json > retry_matrix.json cat retry_matrix.json [] (openpilot) james@Mac sunnypilot % * always * great success * add suffix to retry artifact so it doesn't conflict * retry to get_model too * and there haha * unnecessary hyphen * compare built to missing. include retries * adjust copy of artifacts. * Update build-all-tinygrad-models.yaml * Update model selector versioning and add documentation * Update retry condition for failed models in build-all-tinygrad-models.yaml * Update retry condition for failed models in build-all-tinygrad-models.yaml * Update build-single-tinygrad-model.yaml * false * default none because why not * red diff? i think? * meh ... not needed i guess * error error error * Nayan is watching... always watching mike wazowski * string all the way * lots of retries just in case because im scared * more robust * ONLY ONE!!!!!! * delete.... a lot * fix artifacts * fix artifacts * make sure each is unique :) * skip files like artifact duhhhh * artifact name dir * concurrency * copy here * Update build-single-tinygrad-model.yaml * Update build-single-tinygrad-model.yaml * bump * bump tinygrad * max parallel? if not, i have the other remedy ready in build-all * revert me! * I resynced tinygrad woo hoo * setup shouldnt fail * pull * big ole diff * condition * Update build-all-tinygrad-models.yaml * not always() never always() never!!! * not failure instead of great success * Update build-all-tinygrad-models.yaml * yay that worked. lets invoke build-single one last time * these arent used and are just taking up 250MB space * really frog? * bump back to 3 * self-hosted, tici * rename to trigger tests * 2 and done --------- Co-authored-by: DevTekVE <devtekve@gmail.com>	2025-07-31 09:15:06 -07:00
DevTekVE	3c36374bed	ci: build upstream (tinnygrad) models from our pipeline (#498) ... * Add job to fetch and upload model artifacts Introduced a new `get_model` job to retrieve and upload model artifacts as part of the workflow. Updated the `build_model` job to download and clean up model files before building, ensuring an isolated and streamlined process. These changes improve modularity and artifact handling in the CI pipeline. * Refine model file handling in build workflow Restrict deletion and download commands to ".onnx" files to prevent unintended removal or overwriting of non-ONNX files. This ensures a more targeted and safer workflow for handling model artifacts. * Update model artifact handling in build workflow Changed artifact upload path to include only .onnx files and commented out the deletion of existing models. Also added a dependency for the build stage to ensure proper execution sequence. * Update build workflow to refine model artifact handling Removed unused code for deleting models and fixed the artifact path. Added a reference file logging custom name and upstream branch for better traceability. These changes streamline the workflow and improve clarity. * Set dynamic run-name for sunnypilot build workflow Added a customizable `run-name` field in the sunnypilot build model workflow. This allows more informative and dynamic naming based on input parameters such as `custom_name` or `upstream_branch`. Improves clarity and traceability in workflow runs. * Add customization options and metadata generation to build Introduce new inputs for file name prefix and 20Hz model specification in the workflow. Enable renaming of model files, generation of file hashes, and creation of a `metadata.json` file containing build details. This improves flexibility and enhances artifact information management. * remove EOF * No need for this hack anymore * Add support for compiling ONNX models to Tinygrad format * Add model directory environment variable and metadata generation script * Fix quoting in model generator script command * Refactor conditional flag for 20Hz input in build model script * meh * Add powersave management to build model workflow * Add environment variable setup to build model workflow * make it path call it a day * kill me * kill me x2 * mmm * mmm * Generate metadata.pkl * Generate metadata.pkl * ignore failure on getting model metadata * Cleanup the existing onnxs * Fix rm command syntax in build model script * Cleaning a little * Add optional file name parameter to generate_metadata function * update * stg * linter * more formatting * Update sunnypilot model build workflow: improve custom naming, handle 20Hz default, and add commit date as output. * Update commit date format in workflow script Changed the commit date format in sunnypilot-build-model.yaml to a more human-readable format ('Month DD, YYYY'). This improves readability and consistency in the workflow outputs. * Fix output naming in sunnypilot-build-model workflow Corrected the output name from 'model_date' to 'commit_date' to match its usage. This ensures consistency and prevents potential errors in the workflow. Add debug echo for model date in GitHub workflow This change adds a debug echo statement to display the model date in the sunnypilot-build-model workflow. It helps verify the correct commit date is being set during the workflow process. * Update BUILD_DIR path in sunnypilot workflow Replaced hardcoded BUILD_DIR with a dynamic path using `github.workspace`. This enhances flexibility and ensures compatibility with different environments or runners. * Revert "Update BUILD_DIR path in sunnypilot workflow" This reverts commit 376971b616. * Refactor model metadata generation to use short names Replaced `file_name` with generated `short_name` for metadata and file naming. Introduced `create_short_name` function to simplify short name creation from custom names. Updated scripts and workflow to reflect the new parameter and improve metadata handling. * `Use timezone-aware UTC timestamp for build_time` Updated the code to use `datetime.now(timezone.utc)` instead of `datetime.utcnow()`. This ensures that the generated timestamps are timezone-aware, improving consistency and correctness in the output. * Refactor short name generation logic in model metadata Enhanced the `create_short_name` function to better handle name conversion by incorporating new rules for handling parentheses, alphanumeric words, and version pairs. Updated related variable names in metadata functions for improved clarity and consistency. * Fix syntax error in assigning 'models' key in metadata Corrected a typo where 'models' was missing quotes, causing it to be interpreted as a variable instead of a string key. This ensures proper metadata dictionary structure. Update model metadata structure and JSON generation Revised metadata to include detailed download URIs and a type field for artifacts. Enhanced the JSON generator with new fields like environment, runner, and overrides for better configurability. These changes aim to improve metadata clarity and compatibility with downstream processes. * Refactor variable name from "escaped_name" to "short_name" Renamed "escaped_name" to "short_name" across function parameters and internal logic for clarity and consistency. This improves readability and better aligns with its use case in the metadata generation process. No functional changes were introduced. * Refactor variable names and improve type annotations. Updated parameter names to align with Python naming conventions, enhancing readability and consistency. Added type annotations for function parameters to improve code clarity and maintainability. * Refactor type annotations and clarify comments. Updated type annotations to use "Str" for consistency with custom typing conventions. Improved clarity of a comment describing the normal case logic in the shortening function. * Fix dict formatting in model_generator.py Moved the "overrides" key for better alignment and consistency in the dictionary format. This improves readability without changing functionality. Refactor model short name generation logic Simplify and clarify the `create_short_name` function by improving readability and condensing comments. Adjust casing and truncation logic for single-word cases and handle versioned names more intuitively. * Ensure custom file names are converted to lowercase. When renaming files using a custom short name, enforce lowercase conversion to maintain consistency and prevent potential issues with case-sensitive file systems. This change applies to both the tinygrad and metadata file names. * Use UTC alias for timezone in datetime imports Replaced `timezone.utc` with `UTC` from the `datetime` module for clarity and consistency. This simplifies the representation of time zones and aligns with Python's updated best practices. --------- Co-authored-by: Jason Wen <haibin.wen3@gmail.com>	2025-05-25 10:50:09 +02:00