[ChatQnA] Support the replica tuning for ChatQnA #93
Triggered via pull request
September 9, 2024 09:09
Status
Cancelled
Total duration
1m 30s
Artifacts
–
model_test_hpu.yml
on: pull_request
Matrix: Evaluation-Workflow
Genreate-Report
0s
Annotations
2 errors
Evaluation-Workflow (opt-125m, lambada_openai, hpu, text-generation)
Canceling since a higher priority waiting request for 'Model Test on HPU-116' exists
|
Evaluation-Workflow (opt-125m, lambada_openai, hpu, text-generation)
The operation was canceled.
|