[ZenCPU][Test] Add zentorch/torch version pin consistency test (#52888)

Signed-off-by: Chinmay Kulkarni <Chinmay.Kulkarni@amd.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
This commit is contained in:
Chinmay-Kulkarni-AMD
2026-10-06 13:12:19 +08:00
committed by GitHub
co-authored by Cursor Agent
parent eb2901b735
commit 533d81b4b0
4 changed files with 89 additions and 0 deletions
+3
View File
@@ -241,6 +241,9 @@ export VLLM_VERSION=$(curl -s https://api.github.com/repos/vllm-project/vllm/rel
uv pip install "vllm[zen]" --extra-index-url https://wheels.vllm.ai/${VLLM_VERSION}/cpu --index-strategy first-index --torch-backend cpu
```
!!! warning
`zentorch` is not supported with vLLM 0.27.0 and 0.27.1.
vLLM auto-detects the platform and routes linear layers through ZenDNN-optimized kernels - no flag needed. To verify it is engaged, look for the platform-selection line in the server's startup logs:
```bash