423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-16 00:28:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

Support vllm==0.5.0

Browse Source 
Former-commit-id: e7a8ffd7af21bc3759f055033ba2209fa7a1be0e
This commit is contained in:
Arthur Kim 2024-06-12 16:49:12 +09:00 committed by GitHub
parent 7598b37543
commit 16c7c92396
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: