llama.cpp
vulkan: change graph_compute to be async and enable get_tensor_async
#17158

Merged

vulkan: change graph_compute to be async and enable get_tensor_async #17158

0cc4m merged 4 commits into ggml-org:master from jeffbolznv:graph_compute_async

jeffbolznv requested a review from

0cc4m 63 days ago

github-actions added Vulkan

github-actions added ggml

vulkan: change graph_compute to be async and enable get_tensor_async

12ea0179

fix thread safety errors

60bc85ca

teardown context cleanly

924df57e

jeffbolznv force pushed to 924df57e 63 days ago

Handle async read to non-pinned dst

3343b605

0cc4m approved these changes on 2025-11-15

0cc4m merged 38eaf32a into master 59 days ago

Reviewers

0cc4m

Assignees

No one assigned

Labels

Vulkan ggml

Milestone

No milestone