llama.cpp
sycl: accelerate GLM MLA prefill with MKL flash attention
#29171

Merged

sycl: accelerate GLM MLA prefill with MKL flash attention #29171

ggerganov merged 3 commits into ggml-org:master from anantshri:sycl-glm-mla-mkl-fa

github-actions added testing

github-actions added ggml

github-actions added SYCL

anantshri marked this pull request as ready for review 48 days ago

anantshri requested a review from

ggerganov 48 days ago

anantshri requested a review 48 days ago

arthw approved these changes on 2026-09-21

arthw added merge ready

ggerganov commented on 2026-09-23

ggerganov removed merge ready

anantshri force pushed from 3942532f to 265f9748 45 days ago

arthw commented on 2026-09-29

sycl: accelerate GLM MLA prefill with MKL flash attention

16240ee6

sycl: store MKL flash attention scores in F16

de80753f

Revert "sycl: store MKL flash attention scores in F16"

88e64491

anantshri force pushed from 265f9748 to 88e64491 39 days ago

arthw added merge ready

arthw removed merge ready

arthw approved these changes on 2026-10-06

arthw added merge ready

ggerganov merged d2a79e60 into master 32 days ago

Reviewers

arthw

ggerganov

Assignees

No one assigned

Labels

testing ggml merge ready SYCL

Milestone

No milestone