PR #33794: [GPU] Support int4 in cuDNN GEMM fusions. #33809
Merged
Conversation
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
copybara-service
bot
force-pushed
the
test_830894321
branch
from
b231d21 to
c76defa
Compare
Imported from GitHub PR #33794 📝 Summary of Changes Support int4 in cuDNN GEMM fusions. 🎯 Justification Accelerates some int4 GEMM fusions (under the flag xla_gpu_cudnn_gemm_fusion_level). 🚀 Kind of Contribution ⚡️ Performance Improvement 📊 Benchmark (for Performance Improvements) > Please measure and include speedups for one of the public HLOs in `compiler/xla/tools/benchmarks/hlo/`. These do not use int4. 🧪 Unit Tests: yes 🧪 Execution Tests: yes Copybara import of the project: -- e1b8dc7 by Ilia Sergachev <isergachev@nvidia.com>: [GPU] Support int4 in cuDNN GEMM fusions. Merging this change closes #33794 COPYBARA_INTEGRATE_REVIEW=#33794 from openxla:cudnn_gemm_int4 e1b8dc7 PiperOrigin-RevId: 831264661
copybara-service
bot
force-pushed
the
test_830894321
branch
from
c76defa to
09464f6
Compare
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Outdated suggestions cannot be applied.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.
PR #33794: [GPU] Support int4 in cuDNN GEMM fusions.
Imported from GitHub PR #33794
📝 Summary of Changes
Support int4 in cuDNN GEMM fusions.
🎯 Justification
Accelerates some int4 GEMM fusions (under the flag xla_gpu_cudnn_gemm_fusion_level).
🚀 Kind of Contribution
⚡️ Performance Improvement
📊 Benchmark (for Performance Improvements)
These do not use int4.
🧪 Unit Tests:
yes
🧪 Execution Tests:
yes
Copybara import of the project:
--
e1b8dc7 by Ilia Sergachev isergachev@nvidia.com:
[GPU] Support int4 in cuDNN GEMM fusions.
Merging this change closes #33794
FUTURE_COPYBARA_INTEGRATE_REVIEW=#33794 from openxla:cudnn_gemm_int4 e1b8dc7