frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 23:03:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI Failure] fix models/language/pooling/test_auto_prefix_cache_support.py (#24636)

Browse Source 
Signed-off-by: wang.yuqi <noooop@126.com>
This commit is contained in:
wang.yuqi
2025-09-11 18:31:23 +08:00
committed by GitHub
parent a1213fae5f
commit 25bb9e8c65
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/config/__init__.py
View File

@ -3558,6 +3558,10 @@ class VllmConfig:
disable_chunked_prefill_reasons.append( disable_chunked_prefill_reasons.append(
"Only \"last\" pooling supports chunked " "Only \"last\" pooling supports chunked "
"prefill and prefix caching; disabling both.") "prefill and prefix caching; disabling both.")
if not getattr(self.model_config.hf_config, "is_causal", True):
disable_chunked_prefill_reasons.append(
"Only models using causal attention supports chunked "
"prefill and prefix caching; disabling both.")
elif self.model_config.is_encoder_decoder: elif self.model_config.is_encoder_decoder:
self.scheduler_config.max_num_encoder_input_tokens = \ self.scheduler_config.max_num_encoder_input_tokens = \
MULTIMODAL_REGISTRY.get_encdec_max_encoder_len(self.model_config) MULTIMODAL_REGISTRY.get_encdec_max_encoder_len(self.model_config)