llama.cpp
CUDA: Fix bug in topk-moe for gpt-oss
#16821
Merged

CUDA: Fix bug in topk-moe for gpt-oss #16821

am17an merged 3 commits into ggml-org:master from am17an:fix_topk_cuda
am17an
am17an CUDA: Fix bug in topk-moe for gpt-oss
3449842d
am17an am17an requested a review from slaren slaren 1 year ago
am17an am17an requested a review from JohannesGaessler JohannesGaessler 1 year ago
am17an fix for qwen3 too
91cd070c
JohannesGaessler
JohannesGaessler approved these changes on 2025-10-28
ggerganov
am17an
ggerganov
JohannesGaessler
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
CISC
CISC commented on 2025-10-28
am17an change ifndef to ifdef
5ea78fbf
am17an am17an merged 9a3ea685 into master 1 year ago
am17an am17an deleted the fix_topk_cuda branch 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone