xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-26 12:54:29 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI] Pooling models mteb test disable enforce_eager (#26408)

Browse Source 
Signed-off-by: wang.yuqi <noooop@126.com>
This commit is contained in:
wang.yuqi 2025-10-08 20:15:36 +08:00 committed by GitHub
parent 10c75b5439
commit e39dc46f8f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tests/models/language/generation_ppl_test/ppl_utils.py
View File

@ -51,7 +51,6 @@ def wikitext_ppl_test(
gpu_memory_utilization=0.7,
max_model_len=max_length,
max_num_seqs=1,
enforce_eager=True,
**vllm_extra_kwargs,
) as vllm_model:
# Use max_num_seqs=1 to avoid OOM,

2
tests/models/language/pooling_mteb_test/mteb_utils.py
View File

@ -192,7 +192,6 @@ def mteb_test_embed_models(
model_info.name,
runner="pooling",
max_model_len=None,
enforce_eager=True,
**vllm_extra_kwargs,
) as vllm_model:
model_config = vllm_model.llm.llm_engine.model_config
@ -349,7 +348,6 @@ def mteb_test_rerank_models(
runner="pooling",
max_model_len=None,
max_num_seqs=8,
enforce_eager=True,
**vllm_extra_kwargs,
) as vllm_model:
model_config = vllm_model.llm.llm_engine.model_config