llama.cpp
ggml webgpu: update Vulkan backend CI to use self-hosted runner
#21052

Open

ggml webgpu: update Vulkan backend CI to use self-hosted runner #21052

reeselevine wants to merge 7 commits into ggml-org:master from reeselevine:update-workflows

Update workflows to remove dependence on llvmpipe

48a587ca

reeselevine requested a review 1 day ago

github-actions added devops

Try setting Dawn_DIR

d6ab81fe

remove c++20 initializers

c095e1ec

reeselevine requested a review 1 day ago

github-actions added ggml

github-actions added WebGPU

Move to proper guid

d969d5eb

reeselevine marked this pull request as draft 1 day ago

Try avoiding segfaults on vulkan backend process exit

519eada3

Remove compiler warnings on parameter casting

43685c75

Fix soft_max and update reg_tile accumulation to f32 for better preci…

53ffd67d

Reviewers

No reviews

Assignees

No one assigned

Labels

devops ggml WebGPU

Milestone

No milestone