llama.cpp
[backend](cuda): faster uncontiguous concat
#10760
Merged

[backend](cuda): faster uncontiguous concat #10760

A3shTnT
A3shTnT faster uncontiguous concat
e4189e31
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
JohannesGaessler
JohannesGaessler commented on 2024-12-10
slaren
slaren commented on 2024-12-10
A3shTnT Use a lambda to avoid code duplication
f8a5b044
slaren
slaren commented on 2024-12-11
slaren Update ggml/src/ggml-cuda/concat.cu
618708c5
A3shTnT add constexpr and static assert
9fdf8ad8
A3shTnT
slaren
slaren approved these changes on 2024-12-11
A3shTnT
JohannesGaessler
JohannesGaessler approved these changes on 2024-12-12
A3shTnT
JohannesGaessler JohannesGaessler merged 8faa1d4d into master 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone