llama.cpp
ggml-cuda: disable quantized matvec fusion on all Pascal GPUs
#32239
Merged

ggml-cuda: disable quantized matvec fusion on all Pascal GPUs #32239

dheepakkaran
dheepakkaran ggml-cuda: disable quantized matvec fusion on all Pascal GPUs
4074f5be
dheepakkaran dheepakkaran requested a review 5 days ago
dheepakkaran dheepakkaran requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 5 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-11-14
github-actions github-actions added ggml
github-actions github-actions added CUDA
am17an
am17an approved these changes on 2026-11-14
am17an am17an added merge ready
0cc4m
am17an
dheepakkaran
am17an am17an removed merge ready
am17an
dheepakkaran
ymr-gif
JohannesGaessler
JohannesGaessler approved these changes on 2026-11-17
am17an am17an merged 10152bc4 into master 2 days ago
JohannesGaessler

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone