[cuda backend] skip fully-masked KV blocks calculation in SDPA (#20198) #28
qti-horodnictest-backend-webgpu.yml
on: push
Matrix: test-webgpu / test-backend-linux
Matrix: test-webgpu / test-backend-macos
Waiting for pending jobs
test-webgpu
/
package-golden-artifacts
0s
Annotations
6 errors
|
test-webgpu / test-backend-linux (webgpu, operators) / linux-job
Canceling since a higher priority waiting request for Test WebGPU Backend--6b5273f28983a950c49bc834b50fcef4ab5114c6-false exists
|
|
test-webgpu / test-backend-linux (webgpu, models) / linux-job
Canceling since a higher priority waiting request for Test WebGPU Backend--6b5273f28983a950c49bc834b50fcef4ab5114c6-false exists
|
|
Test WebGPU Backend
Canceling since a higher priority waiting request for Test WebGPU Backend--6b5273f28983a950c49bc834b50fcef4ab5114c6-false exists
|
|
Test WebGPU Backend
Canceling since a higher priority waiting request for Test WebGPU Backend--6b5273f28983a950c49bc834b50fcef4ab5114c6-false exists
|
|
Test WebGPU Backend
Canceling since a higher priority waiting request for Test WebGPU Backend--6b5273f28983a950c49bc834b50fcef4ab5114c6-false exists
|
|
Test WebGPU Backend
Canceling since a higher priority waiting request for Test WebGPU Backend--6b5273f28983a950c49bc834b50fcef4ab5114c6-false exists
|