Repository navigation

CUDA: Allow concurrent streams per split for multi-GPU - #28198

Merged

am17an merged 2 commits into

ggml-org:masterfrom

tannerbruhn:cuda-graph-opt-multi-gpu

Sep 3, 2026

Merged

CUDA: Allow concurrent streams per split for multi-GPU#28198
am17an merged 2 commits into
ggml-org:masterfrom
tannerbruhn:cuda-graph-opt-multi-gpu

Commits on Sep 1, 2026
- CUDA: Allow CUDA optimization per split for multi-GPU.
  tannerbruhn
  committed
  044a1d6
Commits on Sep 2, 2026
- Update ggml/src/ggml-cuda/ggml-cuda.cu
  
  tannerbruhn
  and
  am17an
  authored
  3f4500f