llama.cpp
CUDA: fix Gemma E4B MTP FlashAttention
#25148
Merged

CUDA: fix Gemma E4B MTP FlashAttention #25148

JohannesGaessler
JohannesGaessler CUDA: fix Gemma E4B MTP FlashAttention
254a3acb
JohannesGaessler JohannesGaessler requested a review 33 days ago
github-actions github-actions added ggml
github-actions github-actions added CUDA
ServeurpersoCom
ServeurpersoCom approved these changes on 2026-06-30
am17an
am17an approved these changes on 2026-06-30
JohannesGaessler remove unused template declaration
3237ea2b
EntityDeleter
JohannesGaessler
am17an
am17an approved these changes on 2026-06-30
JohannesGaessler JohannesGaessler merged e495d1e7 into master 32 days ago
Snegovik
EntityDeleter

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone