Skip to content

Switch from fbgemm-gpu w8a8 scaled matmul to vLLM/marlin-kernels #3279

Switch from fbgemm-gpu w8a8 scaled matmul to vLLM/marlin-kernels

Switch from fbgemm-gpu w8a8 scaled matmul to vLLM/marlin-kernels #3279

Triggered via pull request October 24, 2024 15:31
Status Cancelled
Total duration 1m 40s
Artifacts

tests.yaml

on: pull_request
run_tests
0s
run_tests
Fit to window
Zoom out
Zoom in

Annotations

1 error
run_tests
Canceling since a higher priority waiting request for 'Server Tests-feature/cc89-cutlass-w8a8' exists