[Speculative Decoding] Test refactor (vllm-project#8317)

Co-authored-by: youkaichao <[email protected]> Signed-off-by: Alvant <[email protected]>
compressa-ai · Oct 26, 2024 · 86ee231 · 86ee231
1 parent 86f42e1
commit 86ee231
Show file tree

Hide file tree

Showing 12 changed files with 929 additions and 1,044 deletions.
diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml
@@ -217,7 +217,8 @@ steps:
   commands:
     # See https://github.com/vllm-project/vllm/issues/5152
     - export VLLM_ATTENTION_BACKEND=XFORMERS
-    - pytest -v -s spec_decode
+    - pytest -v -s spec_decode/e2e/test_multistep_correctness.py
+    - pytest -v -s spec_decode --ignore=spec_decode/e2e/test_multistep_correctness.py
 
 - label: LoRA Test %N # 30min each
   mirror_hardwares: [amd]