[ChatQnA] Switch to vLLM as default llm backend on Xeon #3138
wangkl2pr-docker-compose-e2e.yml
on: pull_request_target
get-test-matrix
/
Get-test-matrix
5s
Matrix: example-test
Annotations
3 errors and 2 warnings
|
example-test (ChatQnA, xeon) / run-test (test_compose_tgi_on_xeon.sh)
Process completed with exit code 1.
|
|
example-test (ChatQnA, xeon) / run-test (test_compose_without_rerank_on_xeon.sh)
Canceling since a higher priority waiting request for 'E2E test with docker compose-1403' exists
|
|
example-test (ChatQnA, xeon) / run-test (test_compose_without_rerank_on_xeon.sh)
The operation was canceled.
|
|
get-test-matrix / Get-test-matrix
ubuntu-latest pipelines will use ubuntu-24.04 soon. For more details, see https://github.com/actions/runner-images/issues/10636
|
|
example-test (ChatQnA, xeon) / get-test-case
ubuntu-latest pipelines will use ubuntu-24.04 soon. For more details, see https://github.com/actions/runner-images/issues/10636
|
Artifacts
Produced during runtime
| Name | Size | |
|---|---|---|
|
ChatQnA_test_compose_on_xeon.sh
|
165 KB |
|
|
ChatQnA_test_compose_pinecone_on_xeon.sh
|
156 KB |
|
|
ChatQnA_test_compose_qdrant_on_xeon.sh
|
153 KB |
|
|
ChatQnA_test_compose_tgi_on_xeon.sh
|
85.3 KB |
|