Keep official openpilot ancestry and dependency licenses. Store resources directly in Git, remove LFS setup requirements, and leave the downloadable big model outside the source tree.
* Update tinygrad to latest upstream with minimal openpilot patches
* Rebase tinygrad on latest upstream with one remaining patch
* Use retargetable model and warp artifacts
* Pack compiled model weights to reduce startup time
* Memory-map out-of-band model weights
* Use unmodified upstream tinygrad master
* Keep locally built model artifacts native
* Use tinygrad generic ONNX compiler artifacts
* Keep compiler temporary model buffers off device tmpfs
* Keep recurrent model state updates on the GPU
* Use compiled output buffers and swap recurrent state inputs
* Note when ONNX chunk reassembly can be removed
* Bump tinygrad to rebased compilers and AMD queue fix
* Keep recurrent buffers fixed and use faster USB argument updates
* Bump tinygrad for faster model startup
* modeld: use tinygrad ONNX and warp compilers for driving and DM
* Bump tinygrad with current openpilot model compile tests
* modeld: prioritize tinygrad compiler imports in build environment
* Use compiler branch based on openpilot's pinned tinygrad
* modeld: invoke tinygrad compilers without firmware patch
* modeld: RL driving model with 3-file split
Split the driving model into vision + off_policy + on_policy ONNX
files and wire up the RL policy:
- 3-file model split (vision / off_policy / on_policy), replacing the
combined big_driving_policy/vision models
- compiler updates for the split models
- actually consume the policy action in modeld
- add desire state to the driving model
- model iterations (smoothness, off/on-policy weight updates)
* modeld: update driving model
* 1e72cf5a-785f-45ea-888f-28cdb14785de/100
* tinygrad hack
* fix parsing
* looser timing
* big
* Remove unnecessary modeld rebase changes
* Tighten modeld split cleanup
---------
Co-authored-by: Comma Device <device@comma.ai>
Co-authored-by: Armandpl <adpl33@gmail.com>
* 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
* Update Python packages
* not available anymore
* also this
* also this
* maybe?
* version
* try
* Revert "version"
This reverts commit 9ac4401b9ca59677b82736faff8baf66861df5f2.
* revert
* cffi
* issue
* comment
---------
Co-authored-by: Vehicle Researcher <user@comma.ai>
Co-authored-by: Maxime Desroches <desroches.maxime@gmail.com>
firestar5683