ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #4234 from kimdwkimdw/patch-1

Browse Source 
Support vllm==0.5.0

Former-commit-id: 0a9da057c9e7ef11cd709b20263c3d2e4c2d72ed
This commit is contained in:
hoshi-hiyouga
2024-06-12 16:39:09 +08:00
committed by GitHub
parent 7598b37543 16c7c92396
commit c60ea675d7
1 changed files with 4 additions and 1 deletions
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: