llama.cpp
CUDA: add stream-based concurrency
#16991
Open

CUDA: add stream-based concurrency #16991

am17an wants to merge 1 commit into ggml-org:master from am17an:fused-qkv-stream
am17an
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
am17an am17an requested a review from JohannesGaessler JohannesGaessler 2 days ago
am17an am17an force pushed from 1e97a916 to 1c4d8f3b 2 days ago
JohannesGaessler
am17an
am17an CUDA: add stream-based concurrency
70a5a01f
am17an am17an force pushed from 1c4d8f3b to 70a5a01f 2 days ago
IMbackK
am17an
IMbackK

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone