[CUDA] Do not link nvrtc#29705
Merged
Merged
Conversation
Wayne-Ch
approved these changes
Jul 14, 2026
Wayne-Ch
left a comment
Wayne-Ch
left a comment
There was a problem hiding this comment.
Approving from the Foundry Local customer deployment perspective. Removing the hard nvrtc dependency helps reduce unnecessary CUDA runtime dependencies and aligns with the CUDA EP package-size reduction goal. This is not the primary fix for the HY GroupQueryAttention failure, but it is useful for the reduced package direction. Assuming CI completes successfully.
baijumeswani
approved these changes
Jul 14, 2026
Contributor
There was a problem hiding this comment.
Pull request overview
This PR removes explicit linkage to the CUDA NVRTC library from ONNX Runtime’s CUDA provider and CUDA plugin EP build targets, avoiding a hard runtime dependency on the NVRTC shared library/DLL when it isn’t needed by the executed model.
Changes:
- Drop
CUDA::nvrtcfromonnxruntime_providers_cudalink libraries. - Drop
CUDA::nvrtcfromonnxruntime_providers_cuda_pluginlink libraries.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| cmake/onnxruntime_providers_cuda.cmake | Removes CUDA::nvrtc from the main CUDA provider target’s link dependencies. |
| cmake/onnxruntime_providers_cuda_plugin.cmake | Removes CUDA::nvrtc from the CUDA plugin EP target’s link dependencies. |
tianleiwu
enabled auto-merge (squash)
July 16, 2026 16:11
This was referenced Jul 17, 2026
tianleiwu
added a commit
that referenced
this pull request
Jul 18, 2026
This cherry-picks the following commits for the release: | Commit ID | PR Number | Commit Title | |-----------|-----------|-------------| | dd32f35 | #29590 | Fix libcudart.so.13 hard dependency in pybind module breaking import on CPU-only Linux | | cc44a4d | #29706 | [CUDA] Fix XQA GroupQueryAttention cudaErrorInvalidValue on Blackwell (sm_120) | | 23a7e9d | #29705 | [CUDA] Do not link nvrtc | | ee93f83 | #29711 | [CUDA] Update cuda arch list for packages of cuda 12.8 | | fea45a3 | #29620 | [CUDA] Add cuDNN-free ArgMax/ArgMin/ReduceSum and fix LogSoftmax on plugin EP | | f05b218 | #29624 | Enable Spectre-mitigated MSVC libs for BinSkim builds | | 1c89b86 | #29687 | [BUILD] CUDA_QUANT_PREPROCESS off by default and Adjust CI | | 41bd391 | #29658 | [CUDA] Fix null allocator passed to plugin EP kernel PrePack | | 405fbea | #28896 | Add Windows ARM64 CUDA plugin package and align CUDA metadata/artifact naming | | 308f24c | #29622 | Enable fpA_intB GEMM in CUDA builds and add configurable options | | 16ebc1d | #29731 | [Build] Use GPU pool to unblock CI temporarily | |5911a3a263| #29748 | Add OrtErrorCode::ORT_DEVICE_RESET | |6217f73ec5 | #29663 | Fix plugin EP allocator deleter lifetime | --------- Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: GitHub Copilot <copilot@example.com> Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com> Co-authored-by: Yen-Shi Wang <yenshiw@nvidia.com>
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
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.
To avoid hard dependency on nvrtc dll even when it is not used for some models.