linear support deepgemm#4199
Merged
zhyncs merged 13 commits intosgl-project:mainfrom Mar 11, 2025
Merged
Conversation
Collaborator
|
wait for #4255 |
zhyncs
requested review from
HaiShaw,
Ying1123,
ispobock,
merrymercy and
zhyncs
as code owners
zhyncs
reviewed
Mar 10, 2025
| if _is_cuda: | ||
| deep_gemm.gemm_fp8_fp8_bf16_nt((A, As), (B, Bs), C) | ||
| else: | ||
| kernel = ( |
Collaborator
There was a problem hiding this comment.
This is a duplicate. Please delete line 726 of the code.
merrymercy
reviewed
Mar 10, 2025
sleepcoo
force-pushed
the
deepgemm-linear
branch
from
402c4e1 to
c35f45f
Compare
Contributor
6 tasks
Collaborator
|
v0.0.4.post1 is ready |
zhyncs
suggested changes
Mar 10, 2025
Collaborator
zhyncs
left a comment
zhyncs
left a comment
There was a problem hiding this comment.
- ut can't pass on H200
- torch compile not compatible
python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1 --tp 8 --trust-remote-code --enable-torch-compile --torch-compile-max-bs 1
Collaborator
|
ref #3232 |
sleepcoo
force-pushed
the
deepgemm-linear
branch
from
e7b3619 to
1953d05
Compare
Collaborator
Author
wait this deepseek-ai/DeepGEMM#55 |
Collaborator
|
There are still many issues to be fixed in this PR, such as the condition of arch older than hopper, oom of ut, etc., but these are all minor issues that can be resolved in follow-up. |
zhyncs
approved these changes
Mar 11, 2025
67 tasks
hebiao064
pushed a commit
to hebiao064/sglang
that referenced
this pull request
Mar 13, 2025
Co-authored-by: yinfan98 <1106310035@qq.com>
20 tasks
2 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Use deepgemm linear gemm, dependent on #4165
Test case
MMLU Average accuracy: 0.878
performence test