llama.cpp
CUDA: fix crash on large batch size for MoE models
#13384
Merged
Overview
Commits
1
Changes
View On GitHub

CUDA: fix crash on large batch size for MoE models #13384

JohannesGaessler merged 1 commit into ggml-org:master from JohannesGaessler:cuda-fix-moe-max-ub
JohannesGaessler
JohannesGaessler CUDA: fix crash on large batch size for MoE models
819f6c59
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
danielhanchen
danielhanchen
CISC
CISC approved these changes on 2025-05-09
JohannesGaessler JohannesGaessler merged 5c86c9ed into master 341 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Nvidia GPU ggml
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum