llama.cpp
vulkan: sort graph to allow more parallel execution
#15850

Merged

vulkan: sort graph to allow more parallel execution #15850

taronaeo merged 2 commits into ggml-org:master from jeffbolznv:optimize_graph

jeffbolznv requested a review from

slaren 60 days ago

jeffbolznv requested a review from

0cc4m 60 days ago

jeffbolznv force pushed from e71329b3 to 2246c335 60 days ago

jeffbolznv requested a review from

taronaeo 60 days ago

github-actions added Nvidia GPU

github-actions added Vulkan

github-actions added ggml

github-actions added SYCL

github-actions added Apple Metal

github-actions added Ascend NPU

github-actions added OpenCL

github-actions added IBM zDNN

vulkan: sort graph to allow more parallel execution

977ab651

jeffbolznv force pushed from 2246c335 to 977ab651 60 days ago

taronaeo commented on 2025-09-07

slaren commented on 2025-09-08

call optimize_graph per-split

0989ca36

slaren approved these changes on 2025-09-08

taronaeo merged e68aa10d into master 59 days ago

ggerganov commented on 2025-09-11

Reviewers

slaren

ggerganov

taronaeo

0cc4m

Assignees

No one assigned

Labels

Nvidia GPU Vulkan ggml SYCL Apple Metal Ascend NPU OpenCL IBM zDNN

Milestone

No milestone