[Kernels] Enable DeepGEMM by default #24462
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
Signed-off-by: Bill Nell <[email protected]>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request aims to enable DeepGEMM by default. However, the current change only updates a type hint and does not alter the runtime default value. A critical change is needed in vllm/envs.py to actually enable DeepGEMM by default as intended.
tlrmchlsmth
reviewed
Sep 8, 2025
Signed-off-by: Bill Nell <[email protected]>
DeepGEMM is in the docker file and afaik, everything checks |
|
@youkaichao can deepgemm make a pypi release? |
yewentao256
reviewed
Sep 9, 2025
simon-mo
approved these changes
Sep 17, 2025
tlrmchlsmth
approved these changes
Sep 17, 2025
mgoin
approved these changes
Sep 17, 2025
845473182
pushed a commit
to dsxsteven/vllm_splitPR
that referenced
this pull request
Sep 18, 2025
…litPR into model_register * 'model_register' of https://github.com/dsxsteven/vllm_splitPR: (138 commits) Retrieve `sliding_window` from text config in Gemma3 MM (vllm-project#25085) [Docs] Fix API Reference (vllm-project#25140) [Kernel] Better inf handling for grouped topk cu (vllm-project#24886) [CLI] Use streaming in CLI chat and completion commands (vllm-project#23769) [benchmark] add peak throughput metrics and plot (vllm-project#23867) [Spec Decode] Efficient padded speculation (vllm-project#24539) [V0 Deprecation] Remove more V0 tests (vllm-project#25117) [EPLB] Add EPLB support for hunyuan_v1 (vllm-project#23078) [XPU] Whisper model support on XPU Platform (vllm-project#25123) Mark prompt logprobs as incompatible with prompt embeds at API level (vllm-project#25077) [Model] enable data parallel for InternVL vision encoder (vllm-project#23909) [Kernels] Overlap shared experts with combine instead of dispatch (vllm-project#24254) [Bugfix][Qwen3-Next] add prefixes to shared_expert in qwen3-next and mlp in qwen2moe to successfully load ignored params in quantized models (vllm-project#24960) [Core][MM] Cleanup `MultiModalCache` (vllm-project#25006) [Docs] Clean up the contributing README (vllm-project#25099) [MM Encoder] Apply DP ViT for Qwen3-VL model series (vllm-project#24955) [Kernels] Enable DeepGEMM by default (vllm-project#24462) [V0 Deprecation] Skip PP test (vllm-project#25128) [V0 Deprecation] Remove misc V0 tests (vllm-project#25118) [V0 Deprecation] Remove V0 Tracing & Metrics tests (vllm-project#25115) ...
debroy-rh
pushed a commit
to debroy-rh/vllm
that referenced
this pull request
Sep 19, 2025
Signed-off-by: Bill Nell <[email protected]>
FeiDaLI
pushed a commit
to FeiDaLI/vllm
that referenced
this pull request
Sep 25, 2025
Signed-off-by: Bill Nell <[email protected]>
charlifu
pushed a commit
to ROCm/vllm
that referenced
this pull request
Sep 25, 2025
Signed-off-by: Bill Nell <[email protected]> Signed-off-by: charlifu <[email protected]>
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.
Purpose
Enable DeepGEMM kernels by default.
Test Plan
Automated tests.
Test Result
cc @tlrmchlsmth , @yewentao256 , @mgoin , @simon-mo , @WoosukKwon , @youkaichao