Skip to content

Use FP32 working precision for Half LLM sampling #27018

Use FP32 working precision for Half LLM sampling

Use FP32 working precision for Half LLM sampling #27018

Triggered via pull request October 20, 2026 11:40
Status Failure
Total duration 1h 36m 45s
Artifacts –

test-backend-qnn.yml

on: pull_request
test-qnn  /  ...  /  resolve
test-qnn / Resolve CI docker image / resolve
Matrix: test-qnn / test-backend-macos
Waiting for pending jobs
Matrix: test-qnn / test-backend-linux
Waiting for pending jobs
test-qnn  /  package-golden-artifacts
test-qnn / package-golden-artifacts
Fit to window
Zoom out
Zoom in

Annotations

1 error
Test QNN Backend
This workflow run required approval but was not approved before it expired.