p12475398
/
LLaMA-Factory-Mirror
forked from p04798526/LLaMA-Factory-Mirror
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Support vllm==0.5.0

This commit is contained in:
Arthur Kim 2024-06-12 16:49:12 +09:00 committed by GitHub
parent 557891debb
commit d65a3f7cb6
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
src/llamafactory/chat/vllm_engine.py
View File

@ -13,7 +13,10 @@ from .base_engine import BaseEngine, Response
if is_vllm_available(): if is_vllm_available():
from vllm import AsyncEngineArgs, AsyncLLMEngine, RequestOutput, SamplingParams from vllm import AsyncEngineArgs, AsyncLLMEngine, RequestOutput, SamplingParams
from vllm.lora.request import LoRARequest from vllm.lora.request import LoRARequest
from vllm.sequence import MultiModalData try:
from vllm.multimodal import MultiModalData # vllm==0.5.0
except ImportError:
from vllm.sequence import MultiModalData # vllm<0.5.0
if TYPE_CHECKING: if TYPE_CHECKING: