* Remove model chunking and use LFS for Chestnut releases
* Check Git blob sizes once during release packaging
* Download the big model for Chestnut nightly builds
* Reuse published LFS models when pushing releases
* Preserve LFS configuration when copying Chestnut releases
* Detect release builds independently of LFS attributes
* 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
* Reapply "usbgpu: never materialize model weights in RAM" (#38271)
This reverts commit 8196b743af.
* release oob buffers as we load them
* don't leak fds
* lint
* 10s faster loading time for big model
* bigger big
* don't load big model in ram
* patch tg to allow out of band buffers
* dump/load oob
* roundtrip pkl to disk
* streaming chunking
* to_disk
* fixup
* linter
* Revert "bigger big"
This reverts commit 7a8147dd7fab88db963d512ab4008de940714025.
firestar5683