Add CUDA implementation of GatherBlockQuantized operator#25575
Merged
kunal-vaishnavi merged 24 commits intomicrosoft:mainfrom Aug 1, 2025
Merged
Add CUDA implementation of GatherBlockQuantized operator#25575kunal-vaishnavi merged 24 commits intomicrosoft:mainfrom
kunal-vaishnavi merged 24 commits intomicrosoft:mainfrom
Conversation
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
Contributor
|
Please update onnxruntime/test/contrib_ops/gather_block_quantized_op_test.cc to test CUDA EP when it is available. |
Contributor
Author
Working on it |
onnxruntime/contrib_ops/cuda/quantization/gather_block_quantized.cc
Outdated
Show resolved
Hide resolved
onnxruntime/contrib_ops/cuda/quantization/gather_block_quantized.cc
Outdated
Show resolved
Hide resolved
Contributor
Author
|
@microsoft-github-policy-service agree [company="{Microsoft}"] |
onnxruntime/contrib_ops/cuda/quantization/gather_block_quantized.cc
Outdated
Show resolved
Hide resolved
Contributor
Author
|
@microsoft-github-policy-service agree company="Microsoft" |
onnxruntime/contrib_ops/cuda/quantization/gather_block_quantized.cc
Outdated
Show resolved
Hide resolved
onnxruntime/contrib_ops/cuda/quantization/gather_block_quantized.cc
Outdated
Show resolved
Hide resolved
tianleiwu
reviewed
Jul 29, 2025
xiaomsft
force-pushed
the
xiaoh/gather_block_quantized_cuda
branch
from
c8d2587 to
3e352e4
Compare
tianleiwu
reviewed
Jul 30, 2025
tianleiwu
reviewed
Jul 30, 2025
onnxruntime/contrib_ops/cuda/quantization/gather_block_quantized.cu
Outdated
Show resolved
Hide resolved
xiaomsft
force-pushed
the
xiaoh/gather_block_quantized_cuda
branch
from
3e352e4 to
bb04d4c
Compare
Contributor
|
/azp run Linux QNN CI Pipeline, Win_TRT_Minimal_CUDA_Test_CI, Windows ARM64 QNN CI Pipeline, Windows GPU Doc Gen CI Pipeline, Windows x64 QNN CI Pipeline |
|
Azure Pipelines successfully started running 5 pipeline(s). |
1 similar comment
|
Azure Pipelines successfully started running 5 pipeline(s). |
tianleiwu
previously approved these changes
Aug 1, 2025
added 8 commits
August 1, 2025 10:42
added 14 commits
August 1, 2025 10:42
xiaomsft
force-pushed
the
xiaoh/gather_block_quantized_cuda
branch
from
7be0d43 to
0c7938e
Compare
kunal-vaishnavi
approved these changes
Aug 1, 2025
tianleiwu
approved these changes
Aug 1, 2025
Contributor
|
/azp run Linux QNN CI Pipeline, Win_TRT_Minimal_CUDA_Test_CI, Windows ARM64 QNN CI Pipeline, Windows GPU Doc Gen CI Pipeline, Windows x64 QNN CI Pipeline |
|
Azure Pipelines successfully started running 5 pipeline(s). |
sophies927
pushed a commit
that referenced
this pull request
Aug 2, 2025
### Description This PR implements GatherBlockQuantized operator for CUDA EP with 4 bit and 8 bit data support. ### Motivation and Context GatherBlockQuantified operator is essential for MOE model's expert selection, especially when the model has been statically quantized. --------- Co-authored-by: Xiaoyan Hu <xiaoh@microsoft.com>
sanketkaleoss
pushed a commit
to sanketkaleoss/onnxruntime
that referenced
this pull request
Aug 11, 2025
…5575) ### Description This PR implements GatherBlockQuantized operator for CUDA EP with 4 bit and 8 bit data support. ### Motivation and Context GatherBlockQuantified operator is essential for MOE model's expert selection, especially when the model has been statically quantized. --------- Co-authored-by: Xiaoyan Hu <xiaoh@microsoft.com>
gedoensmax
pushed a commit
to gedoensmax/onnxruntime
that referenced
this pull request
Sep 2, 2025
…5575) ### Description This PR implements GatherBlockQuantized operator for CUDA EP with 4 bit and 8 bit data support. ### Motivation and Context GatherBlockQuantified operator is essential for MOE model's expert selection, especially when the model has been statically quantized. --------- Co-authored-by: Xiaoyan Hu <xiaoh@microsoft.com>
tianleiwu
pushed a commit
that referenced
this pull request
Sep 4, 2025
### Description This PR implements GatherBlockQuantized operator for CUDA EP with 4 bit and 8 bit data support. ### Motivation and Context GatherBlockQuantified operator is essential for MOE model's expert selection, especially when the model has been statically quantized. --------- Co-authored-by: Xiaoyan Hu <xiaoh@microsoft.com>
tianleiwu
added
cherry-picked
jywu-msft
pushed a commit
that referenced
this pull request
Sep 5, 2025
### Description Cherry-pick the following PRs: #25943 #25937 #25917 #25909 #25898 #25897 #25888 #25881 #25830 #25619 #25575 #25572 #25558 #25530 #25474 #25455 #25110 Also two dependent PRs for qMoE cpu: #25877 #25822 --------- Co-authored-by: xiaomsft <136376084+xiaomsft@users.noreply.github.com> Co-authored-by: Xiaoyan Hu <xiaoh@microsoft.com> Co-authored-by: Akshay Sonawane <111780983+apsonawane@users.noreply.github.com> Co-authored-by: Kunal Vaishnavi <kvaishnavi@microsoft.com> Co-authored-by: Pradeep Sakhamoori <psakhamoori@microsoft.com> Co-authored-by: mingyue <131847423+mingyueliuh@users.noreply.github.com> Co-authored-by: Maximilian Müller <44298237+gedoensmax@users.noreply.github.com> Co-authored-by: Adrian Lizarraga <adlizarraga@microsoft.com> Co-authored-by: Dmitri Smirnov <yuslepukhin@users.noreply.github.com> Co-authored-by: Emmanuel <91394589+kobby-kobbs@users.noreply.github.com> Co-authored-by: Emmanuel Assumang <eassumang@microsoft.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: praneshgo <pranesh.iitp@gmail.com> Co-authored-by: Hariharan Seshadri <shariharan91@gmail.com> Co-authored-by: Jing Fang <fajin@microsoft.com> Co-authored-by: Ishwar Raut <iraut@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
4 participants
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.
Description
This PR implements GatherBlockQuantized operator for CUDA EP with 4 bit and 8 bit data support.
Motivation and Context
GatherBlockQuantified operator is essential for MOE model's expert selection, especially when the model has been statically quantized.