[ATOM-SGL][Attn refrac] Route DeepSeek MLA through an SGLang wrapper#29
Open
ZhiweiYan-96 wants to merge 1 commit into
Open
[ATOM-SGL][Attn refrac] Route DeepSeek MLA through an SGLang wrapper#29ZhiweiYan-96 wants to merge 1 commit into
ZhiweiYan-96 wants to merge 1 commit into
Conversation
Move the SGLang DeepSeek MLA runtime entry from legacy forward glue into SGLangDeepseekMLAAttention while keeping RadixAttention and the full-attention backend as the host/backend layers. Shrink deepseek_mla_forward.py into a helper module and clarify absorbed vs non-absorbed path naming.
ZhiweiYan-96
force-pushed
the
zhiwei/attn_model_decouple
branch
from
67d67b9 to
3598254
Compare
ZhiweiYan-96
force-pushed
the
zhiwei/attn_refrac_share_model
branch
from
2a3dd89 to
a1f88ae
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Move the SGLang DeepSeek MLA runtime entry from legacy forward glue into SGLangDeepseekMLAAttention while keeping RadixAttention and the full-attention backend as the host/backend layers. Shrink deepseek_mla_forward.py into a helper module and clarify absorbed vs non-absorbed path naming.