Skip to content

[Feat][Graph] Support FULL_DECODE_ONLY mode for GQA/MHA models #9354

[Feat][Graph] Support FULL_DECODE_ONLY mode for GQA/MHA models

[Feat][Graph] Support FULL_DECODE_ONLY mode for GQA/MHA models #9354

Triggered via pull request August 15, 2025 11:41
Status Failure
Total duration 48m 30s
Artifacts

vllm_ascend_test.yaml

on: pull_request
Matrix: singlecard e2e test
Matrix: unit test
Matrix: multicard e2e test
Fit to window
Zoom out
Zoom in

Annotations

3 errors
singlecard e2e test (linux-aarch64-a2-1, main)
Executing the custom container implementation failed. Please contact your self hosted runner administrator.
singlecard e2e test (linux-aarch64-a2-1, main)
Process completed with exit code 1.
singlecard e2e test (linux-aarch64-a2-1, main)
Error: failed to run script step: command terminated with non-zero exit code: Error executing in Docker Container: 1