llama.cpp
vulkan: sparse flash attention for quantized K/V
#29639

Merged

vulkan: sparse flash attention for quantized K/V #29639

0cc4m merged 2 commits into ggml-org:master from fxgsell:vk-sparse-fa-quant

vulkan: sparse flash attention for quantized K/V

61be16b6

fxgsell requested a review from

ggerganov 15 days ago

fxgsell requested a review 15 days ago

github-actions added testing

github-actions added Vulkan

github-actions added ggml

vulkan: single-scan sparse FA index compaction

0cdb384c

jeffbolznv approved these changes on 2026-10-03

0cc4m approved these changes on 2026-10-05

0cc4m merged b3daa077 into master 9 days ago

Reviewers

0cc4m

jeffbolznv

ggerganov

Assignees

No one assigned

Labels

testing Vulkan ggml

Milestone

No milestone