llama.cpp
[CUDA] Added a cudaMemcpy2DAsync fast path to ggml_cuda_cpy
#25057
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
3
Changes
View On
GitHub
[CUDA] Added a cudaMemcpy2DAsync fast path to ggml_cuda_cpy
#25057
gaugarg-nv
merged 3 commits into
ggml-org:master
from
gaugarg-nv:fast_ggml_cpy
[CUDA] Added a cudaMemcpy2DAsync fast path to ggml_cuda_cpy
0efe40e4
gaugarg-nv
requested a review
5 days ago
github-actions
added
ggml
github-actions
added
CUDA
am17an
approved these changes on 2026-06-27
Add new tests that execute the new optimized strided copy path
86474fae
gaugarg-nv
requested a review
from
ggerganov
5 days ago
github-actions
added
testing
Return unsupported for strided copy in OpenVINO, as new tests are faiā¦
e78d7d20
github-actions
added
OpenVINO
ggerganov
approved these changes on 2026-06-27
gaugarg-nv
merged
0ed235ea
into master
4 days ago
gaugarg-nv
deleted the fast_ggml_cpy branch
4 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
ggerganov
am17an
Assignees
No one assigned
Labels
testing
ggml
CUDA
OpenVINO
Milestone
No milestone
Login to write a write a comment.
Login via GitHub