fix: eliminate onnxruntime-gpu install churn in Docker TensorRT FP8 step#33
Open
forkni wants to merge 1 commit into
Open
fix: eliminate onnxruntime-gpu install churn in Docker TensorRT FP8 step#33forkni wants to merge 1 commit into
forkni wants to merge 1 commit into
Conversation
nvidia-modelopt[onnx] (unbounded, floats to 0.45.0) hard-pins onnxruntime-gpu==1.22.0 on Windows and force-upgrades onnx to 1.21.0, which breaks FP8 quant (external-data loading -> negative QDQ scale). Pin modelopt==0.43.0 (the proven pin used by the installer's TD path) and drop the [onnx] extra, enumerating its deterministic deps explicitly instead — modelopt core has no onnx requirement, so the onnx==1.19.1/onnxruntime-gpu==1.24.4 pins installed just above are never perturbed. Mirrors the same fix landed in forkni/StreamDiffusion-installer#4. Co-authored-by: Claude Opus 5 <[email protected]>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
src/streamdiffusion/tools/install-tensorrt.py(used by the Dockerfiles) requestednvidia-modelopt[onnx], whose[onnx]extra hard-pinsonnxruntime-gpu==1.22.0on Windows and, left unbounded, floats modelopt to a version that force-upgradesonnxto 1.21.0 and breaks FP8 quantization.nvidia-modelopt==0.43.0and drops the[onnx]extra, enumerating its remaining deterministic deps explicitly (cppimport,lief,ml_dtypes,onnxconverter-common~=1.16.0) so the already-installedonnx/onnxruntime-gpupins from the step above are never touched.forkni/StreamDiffusion@SDTD_040_beta_release(internal PR feat: FP8 quantization robustness, quality harness, kvo_cache patch #14).Test plan
SDTD_040_beta_releasetip, no conflicts.src/streamdiffusion/tools/install-tensorrt.py).pip install --dry-runand a full clean install (companion Windows installer fix, tested locally): noonnxruntime-gpudownload/uninstall churn in the FP8 step, final stateonnxruntime-gpu==1.24.4,onnx==1.19.1,nvidia-modelopt==0.43.0.