xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-23 05:44:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bug] Fix Test in Batch Invariant (#26128)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye 2025-10-08 13:13:47 -04:00 committed by GitHub
parent 6273fe8d3d
commit 4ba8875749
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tests/v1/generation/test_batch_invariance.py
View File

@ -292,8 +292,11 @@ def LLM_with_max_seqs(
# Allow some CPU offload if needed.
swap_space=swap_space,
# Keep things lean and CI-friendly.
dtype="float16",
dtype="auto",
# Single-GPU by default; override externally if desired.
tensor_parallel_size=int(os.getenv("VLLM_TP_SIZE", "1")),
trust_remote_code=os.getenv("VLLM_TRUST_REMOTE_CODE", "0") == "1",
enable_prefix_caching=False,
# Enable for MOE models
# enable_expert_parallel=True,
)