[CPU] Fix argument issues in qkv_proj_with_rope_fused_weight and bmm…#21367
Merged
mingfeima merged 8 commits intosgl-project:mainfrom Apr 13, 2026
Merged
[CPU] Fix argument issues in qkv_proj_with_rope_fused_weight and bmm…#21367mingfeima merged 8 commits intosgl-project:mainfrom
mingfeima merged 8 commits intosgl-project:mainfrom
Conversation
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
Contributor
Author
|
/tag-run-ci-label |
Fridge003
approved these changes
Apr 9, 2026
971a858 to
f977d67
Compare
rainj-me
approved these changes
Apr 10, 2026
pyc96
pushed a commit
to pyc96/sglang
that referenced
this pull request
Apr 14, 2026
…sgl-project#21367) Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
yhyang201
pushed a commit
to yhyang201/sglang
that referenced
this pull request
Apr 22, 2026
…sgl-project#21367) Co-authored-by: Ma Mingfei <mingfei.ma@intel.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
…_cpu
Motivation
This PR fixes the following issue encountered when running DeepSeek-V3.1-Terminus:
w_scaleis only required for FP8 in the kernelsqkv_proj_with_rope_fused_weightandbmm_cpu, so we updated the frontend logic to passw_scale=Nonefor other data types.command:
python -m sglang.launch_server --model IntervitensInc/DeepSeek-V3.1-Terminus-Channel-int8 --trust-remote-code --disable-overlap-schedule --device cpu --quantization w8a8_int8 --tp 6RuntimeError: sgl_kernel::qkv_proj_with_rope_fused_weight() Expected a value of type 'Optional[Tensor]' for argument 'w_scale' but instead found type 'float'.
Modifications
Accuracy Tests
Benchmarking and Profiling
Checklist
Review Process
/tag-run-ci-label,/rerun-failed-ci,/tag-and-rerun-ci