llama.cpp
opencl: optimize mul_mat_f16_f32 for decode
#24504
Merged

opencl: optimize mul_mat_f16_f32 for decode #24504

lhez
lhez opencl: optimize mul_mat_f16_f32_l4 for decode
dc0537d4
github-actions github-actions added ggml
github-actions github-actions added OpenCL
lhez lhez marked this pull request as ready for review 75 days ago
lhez lhez requested a review 75 days ago
max-krasnyansky
max-krasnyansky approved these changes on 2026-06-16
lhez
taronaeo
taronaeo approved these changes on 2026-06-17
max-krasnyansky max-krasnyansky merged 51571722 into master 74 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone