llama.cpp
sycl: flash-attention implementation
#16969
Open

sycl: flash-attention implementation #16969

ye-NX wants to merge 6 commits into ggml-org:master from ye-NX:saf-ye/flash-attn
ye-NX
ye-NX sycl: initialize flash-attention implementation
fc0e0413
github-actions github-actions added ggml
github-actions github-actions added SYCL
NeoZhangJianyu
NeoZhangJianyu commented on 2025-11-04
CISC
CISC commented on 2025-11-04
safranowith Update ggml/src/ggml-sycl/flash-attn/flash-attn-sycl.cpp
dd1fde5b
safranowith Update ggml/src/ggml-sycl/flash-attn/flash-attn-sycl.cpp
4f52591e
ye-NX Update ggml/src/ggml-sycl/flash-attn/flash-attn-sycl.cpp
af5b6446
safranowith safranowith force pushed from 693157c8 to af5b6446 2 days ago
safranowith add include in ggml-sycl.cpp
8e8fb573
safranowith remove unrelated changes
dcd7ca52
safranowith safranowith force pushed from fdf83f7c to dcd7ca52 2 days ago
NeoZhangJianyu
ye-NX

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone