Use tinygrad generic ONNX compiler artifacts (#38926)

* 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
This commit is contained in:
Harald Schäfer
2026-09-15 18:01:25 -07:00
committed by GitHub
parent f15544b482
commit 81ae1a2e2d
5 changed files with 50 additions and 32 deletions
+1 -1
View File
@@ -16,4 +16,4 @@
[submodule "tinygrad"]
path = tinygrad_repo
url = https://github.com/commaai/tinygrad.git
branch = openpilot-modeld-test
branch = model-warp-compile