sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float #9332
nihuilinux-x64-gpu-gcc.yml
on: pull_request
linux-gcc-gpu
3m 49s
linux-gcc-gpu-system-glslang
3m 47s
linux-gcc-gpu-t4
3m 47s
Annotations
7 errors
|
linux-gcc-gpu-system-glslang
Canceling since a higher priority waiting request for linux-x64-gpu-gcc-refs/pull/6923/merge exists
|
|
linux-gcc-gpu-system-glslang
The operation was canceled.
|
|
linux-gcc-gpu
Canceling since a higher priority waiting request for linux-x64-gpu-gcc-refs/pull/6923/merge exists
|
|
linux-gcc-gpu
The operation was canceled.
|
|
linux-gcc-gpu-t4
Canceling since a higher priority waiting request for linux-x64-gpu-gcc-refs/pull/6923/merge exists
|
|
linux-gcc-gpu-t4
The operation was canceled.
|
|
linux-x64-gpu-gcc
Canceling since a higher priority waiting request for linux-x64-gpu-gcc-refs/pull/6923/merge exists
|