xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-09 17:27:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix pre-commit

Browse Source 
Signed-off-by: bk-201 <joy25810@foxmail.com>
This commit is contained in:
bk-201 2025-12-23 02:48:23 +00:00
parent a9b9af91b2
commit 390ac9a4a4
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/v1/engine/input_processor.py
View File

@ -416,7 +416,11 @@ class InputProcessor:
vary depending on the LoRA request. Therefore, the mm_hash must be vary depending on the LoRA request. Therefore, the mm_hash must be
generated based on the LoRA request to prevent incorrect cache hits. generated based on the LoRA request to prevent incorrect cache hits.
""" """
if lora_request is None or not self.lora_config.enable_tower_connector_lora: if (
lora_request is None
or self.lora_config is None
or not self.lora_config.enable_tower_connector_lora
):
return mm_hash return mm_hash
return f"{lora_request.lora_name}:{mm_hash}" return f"{lora_request.lora_name}:{mm_hash}"