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

[cli] support lazy import (#9217)

Browse Source 
Co-authored-by: frozenleaves <frozen@Mac.local>
This commit is contained in:
魅影
2025-09-30 18:02:26 +08:00
committed by GitHub
parent 6ffebe5ff7
commit a04d777d7f
2 changed files with 60 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
src/llamafactory/chat/chat_model.py
View File

@@ -24,9 +24,6 @@ from typing import TYPE_CHECKING, Any, Optional
from ..extras.constants import EngineName
from ..extras.misc import torch_gc
from ..hparams import get_infer_args
from .hf_engine import HuggingfaceEngine
from .sglang_engine import SGLangEngine
from .vllm_engine import VllmEngine
if TYPE_CHECKING:
@@ -49,12 +46,28 @@ class ChatModel:
def __init__(self, args: Optional[dict[str, Any]] = None) -> None:
model_args, data_args, finetuning_args, generating_args = get_infer_args(args)
if model_args.infer_backend == EngineName.HF:
from .hf_engine import HuggingfaceEngine
self.engine: BaseEngine = HuggingfaceEngine(model_args, data_args, finetuning_args, generating_args)
elif model_args.infer_backend == EngineName.VLLM:
self.engine: BaseEngine = VllmEngine(model_args, data_args, finetuning_args, generating_args)
try:
from .vllm_engine import VllmEngine
self.engine: BaseEngine = VllmEngine(model_args, data_args, finetuning_args, generating_args)
except ImportError as e:
raise ImportError(
"vLLM not install, you may need to run `pip install vllm`\n"
"or try to use HuggingFace backend: --infer_backend huggingface"
) from e
elif model_args.infer_backend == EngineName.SGLANG:
self.engine: BaseEngine = SGLangEngine(model_args, data_args, finetuning_args, generating_args)
try:
from .sglang_engine import SGLangEngine
self.engine: BaseEngine = SGLangEngine(model_args, data_args, finetuning_args, generating_args)
except ImportError as e:
raise ImportError(
"SGLang not install, you may need to run `pip install sglang[all]`\n"
"or try to use HuggingFace backend: --infer_backend huggingface"
) from e
else:
raise NotImplementedError(f"Unknown backend: {model_args.infer_backend}")