Use a precompiled eGPU driving model (#38930)

* Ship precompiled eGPU model and camera warps

Compile f78ed37d-afad-4dbc-8050-40ea885eedde/12864 through xx/ml_tools/openpilot_compile using the pinned tinygrad version.

* Precompile the existing master driving model

Use the unchanged master ONNX (SHA-256 6fee5937923c74848df4a63f6239eb6331c6274dd4bdb7a5d6ec0388a8b543d5) instead of updating the trained model.

* Compile camera warps on device

* Remove obsolete ONNX chunking and big model build check

* Chunk model artifacts only during release packaging

* Require model and camera warps for Chestnut readiness

* Recompile precompiled CPU helpers for the runtime host

* Ship the eGPU model with an ARM submission helper

* Exempt model pickles from the build product size limit
This commit is contained in:
Harald Schäfer
2026-09-16 08:13:45 -07:00
committed by GitHub
parent 81ae1a2e2d
commit 6080cc6168
17 changed files with 39 additions and 72 deletions
+1 -1
View File
@@ -18,7 +18,7 @@ concurrency:
env:
GIT_CONFIG_COUNT: 1
GIT_CONFIG_KEY_0: lfs.fetchexclude
GIT_CONFIG_VALUE_0: openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx
GIT_CONFIG_VALUE_0: openpilot/selfdrive/modeld/models/big_driving_tinygrad.pkl
jobs:
docs: