xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 04:44:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Docs] Lazy import gguf (#20785)

Browse Source 
Signed-off-by: simon-mo <simon.mo@hey.com>
This commit is contained in:
Simon Mo 2025-07-10 16:06:37 -07:00 committed by GitHub
parent 5b6fe23d05
commit b854321ffe
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/entrypoints/score_utils.py
View File

@ -11,7 +11,6 @@ from vllm.entrypoints.chat_utils import (
ChatCompletionContentPartImageParam, ChatCompletionContentPartTextParam,
MultiModalItemTracker, _ContentPart, _parse_chat_message_content_part)
from vllm.inputs import TokensPrompt
from vllm.model_executor.model_loader import get_model_cls
from vllm.model_executor.models.interfaces import supports_score_template
from vllm.multimodal.inputs import MultiModalDataDict
from vllm.outputs import PoolingRequestOutput
@ -140,6 +139,8 @@ def apply_score_template(
prompt_1: str,
prompt_2: str,
) -> str:
# NOTE(Simon): lazy import to avoid bring in all dependencies (e.g. gguf)
from vllm.model_executor.model_loader import get_model_cls
model = get_model_cls(model_config)
if supports_score_template(model):
@ -162,6 +163,9 @@ def post_process_tokens(
Note:
This is an in-place operation.
"""
# NOTE(Simon): lazy import to avoid bring in all dependencies (e.g. gguf)
from vllm.model_executor.model_loader import get_model_cls
model = get_model_cls(model_config)
if supports_score_template(model):
model.post_process_tokens(prompt)

6
vllm/model_executor/model_loader/weight_utils.py
View File

@ -14,7 +14,6 @@ from pathlib import Path
from typing import Any, Callable, Optional, Union
import filelock
import gguf
import huggingface_hub.constants
import numpy as np
import torch
@ -40,6 +39,11 @@ except (ImportError, OSError):
SafetensorsStreamer = runai_model_streamer.placeholder_attr(
"SafetensorsStreamer")
try:
import gguf
except ImportError:
gguf = PlaceholderModule("gguf")
try:
from fastsafetensors import SafeTensorsFileLoader, SingleGroup
except ImportError: