llama.cpp
CUDA: enable sparse fa for qwen4
#28770
Merged

CUDA: enable sparse fa for qwen4 #28770

am17an merged 1 commit into master from aman/qwen-sparse
am17an
am17an CUDA: enable sparse fa for qwen4
41a4ad00
am17an am17an requested a review from ggerganov ggerganov 63 days ago
am17an am17an requested a review from CISC CISC 63 days ago
am17an am17an requested a review 63 days ago
github-actions github-actions added model
github-actions github-actions added testing
github-actions github-actions added ggml
github-actions github-actions added CUDA
JohannesGaessler
JohannesGaessler approved these changes on 2026-09-12
JohannesGaessler
JohannesGaessler JohannesGaessler assigned JohannesGaessler JohannesGaessler 62 days ago
am17an
am17an am17an added merge ready
ggerganov
ggerganov approved these changes on 2026-09-20
am17an
am17an am17an merged 3cf03257 into master 54 days ago
ServeurpersoCom
JohannesGaessler

Login to write a write a comment.

Login via GitHub

Assignees
Labels
Milestone