feat(sparsity): add VecAttention sparse prefill for VLM#320
Merged
Conversation
Integrate VecAttention into AngelSlim as a sparse attention method for Vision-Language Models (Qwen2.5-VL). - Add vecattention subpackage under compressor/sparsity/ - Add vllm-flash-attention as git submodule for sparse_attn_func kernel - Add Triton kernels for MinP threshold selection and query pooling - Add run_vecattention.py tool for image/video inference
yghstill
previously approved these changes
May 28, 2026
anminliu
force-pushed
the
dev_vecattention
branch
from
033eb00 to
3197960
Compare
yghstill
approved these changes
May 29, 2026
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Integrate VecAttention into AngelSlim as a sparse attention method for Vision-Language Models (Qwen2.5-VL).