[shortfin llm integration tests] Add tinystories llama2 25m model as a smoke test #691
renxidapkgci.yml
on: pull_request
Build Packages
/
setup_metadata
9s
Matrix: Build Packages / build_packages
Matrix: Test shark-ai / Integration Tests - Shortfin LLM Server
Annotations
3 errors and 3 warnings
|
Test shark-ai / Integration Tests - Shortfin LLM Server (amdgpu_rocm_mi300_gfx942, linux-mi300-1gpu-ossci, gfx942...
Canceling since a higher priority waiting request for 'PkgCI-936' exists
|
|
Test shark-ai / Integration Tests - Shortfin LLM Server (cpu, azure-cpubuilder-linux-scale, cpu, 3.11)
Canceling since a higher priority waiting request for 'PkgCI-936' exists
|
|
Test shark-ai / Integration Tests - Shortfin LLM Server (cpu, azure-cpubuilder-linux-scale, cpu, 3.11)
The operation was canceled.
|
|
Build Packages / sharktank :: linux-x86_64 :: cp311-cp311
Cache not found for keys: build-packages-sharktank-linux-x86_64-cp311-cp311-v1-9c62a4474c766306f99daa459f29bd55d36e466d, build-packages-sharktank-linux-x86_64-cp311-cp311-v1-
|
|
Build Packages / shark-ai :: linux-x86_64 :: cp311-cp311
Cache not found for keys: build-packages-shark-ai-linux-x86_64-cp311-cp311-v1-9c62a4474c766306f99daa459f29bd55d36e466d, build-packages-shark-ai-linux-x86_64-cp311-cp311-v1-
|
|
Test shark-ai / Integration Tests - Shortfin LLM Server (cpu, azure-cpubuilder-linux-scale, cpu, 3.11)
Cache not found for keys: Linux-uv-py3.11-b5cf6b70a8e0c6c9b24bc9bedd5703dbfda3bb5e040108fef268ac88944372df
|
Artifacts
Produced during runtime
| Name | Size | |
|---|---|---|
|
snapshot-shark-ai-linux-x86_64-cp311-cp311
|
1.31 KB |
|
|
snapshot-sharktank-linux-x86_64-cp311-cp311
|
274 KB |
|
|
snapshot-shortfin-linux-x86_64-cp310-cp310
|
1.24 MB |
|
|
snapshot-shortfin-linux-x86_64-cp311-cp311
|
1.24 MB |
|
|
snapshot-shortfin-linux-x86_64-cp312-cp312
|
1.24 MB |
|
|
snapshot-shortfin-linux-x86_64-cp313-cp313
|
1.24 MB |
|
|
snapshot-shortfin-linux-x86_64-cp313-cp313t
|
1.24 MB |
|
|
version_local_files
|
696 Bytes |
|