Skip to content

Fix onnxruntime-gpu churn in Docker TensorRT FP8 install step#15

Merged
forkni merged 1 commit into
SDTD_032_devfrom
integ/trt-modelopt-pin-to-032
Jul 19, 2026
Merged

Fix onnxruntime-gpu churn in Docker TensorRT FP8 install step#15
forkni merged 1 commit into
SDTD_032_devfrom
integ/trt-modelopt-pin-to-032

Conversation

@forkni

@forkni forkni commented Jul 19, 2026

Copy link
Copy Markdown
Owner

Summary

  • nvidia-modelopt[onnx] was unbounded here, floating to 0.45.0 — whose [onnx] extra force-upgrades onnx to 1.21.0 (breaks FP8 quant: external-data loading -> negative QDQ scale) and hard-pins onnxruntime-gpu==1.22.0 on Windows, downgrading off the onnx==1.19.1/onnxruntime-gpu==1.24.4 pins installed just above.
  • Pin nvidia-modelopt==0.43.0 (the same proven pin already used in forkni/StreamDiffusion-installer) and drop the [onnx] extra, enumerating its deterministic deps explicitly instead. modelopt core has no onnx requirement, so the churn/regression never enters the resolve.
  • Mirrors Fix onnxruntime-gpu churn in TensorRT FP8 install step StreamDiffusion-installer#4 and Fix onnxruntime-gpu churn in Docker TensorRT FP8 install step #14 (SDTD_040_beta_release, both already merged), applied here to the same Docker/Linux-only tool on SDTD_032_dev.

Test plan

  • py_compile src/streamdiffusion/tools/install-tensorrt.py passes
  • Confirmed this file was byte-identical to the pre-patch SDTD_040_beta_release copy before patching, so the same enumeration verified via pip --dry-run on 040 applies unchanged

🤖 Generated with Claude Code

@forkni @claude
Fix onnxruntime-gpu churn in Docker TensorRT FP8 install step
dd99f0b 
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
and #14 (SDTD_040_beta_release).

Co-Authored-By: Claude Opus 5 <[email protected]>
@claude

claude Bot commented Jul 19, 2026 •
edited
Loading

Copy link
Copy Markdown

Claude finished @forkni's task in 2m 20s —— View job

Code review

Summary: This PR pins nvidia-modelopt==0.43.0 and drops its [onnx] extra in src/streamdiffusion/tools/install-tensorrt.py, replacing it with an explicit enumeration of the extra's remaining deps. This avoids the extra pulling in onnx==1.21.0 / downgrading onnxruntime-gpu off the pins installed a few lines above. The change is scoped to a single 13-line block, Docker/Linux-only CUDA-12 install path.

No issues found. Checked for bugs, logic errors, and dependency-resolution problems in the diff.

One candidate concern was investigated and ruled out: cppimport, lief, and ml_dtypes are added unpinned in the new command. However, this is not a regression introduced by this PR — the previous nvidia-modelopt[onnx] already pulled these same transitive deps with the same (absent) version constraints, since pip extras don't add extra pinning beyond what's declared. This PR just makes the resolution explicit; behavior is unchanged.

@forkni
forkni merged commit 5e79862 into SDTD_032_dev Jul 19, 2026
1 check passed
@forkni
forkni deleted the integ/trt-modelopt-pin-to-032 branch July 19, 2026 15:02
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@forkni