biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Core] Dynamic image size support for VLMs (#5276)

Browse Source 
Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: ywang96 <ywang@roblox.com>
Co-authored-by: xwjiang2010 <87673679+xwjiang2010@users.noreply.github.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2024-07-03 11:34:00 +08:00
committed by GitHub
parent 482045ee77
commit 9831aec49f
38 changed files with 1453 additions and 664 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
vllm/config.py
View File

@@ -5,7 +5,7 @@ from typing import (TYPE_CHECKING, Any, ClassVar, Dict, List, Optional, Tuple,
Union)
import torch
from transformers import PretrainedConfig, PreTrainedTokenizerBase
from transformers import PretrainedConfig
import vllm.envs as envs
from vllm.logger import init_logger
@@ -1303,16 +1303,6 @@ class VisionLanguageConfig:
image_input_shape: tuple
image_feature_size: int
#TODO(ywang96): make this a cached property once we refactor the
# VisionLanguageConfig class.
def get_image_token_text(
self, tokenizer: PreTrainedTokenizerBase) -> Tuple[str, str]:
"""Get the image token placeholder text to be inserted into the
text prompt and the string representation of the image token id.
"""
image_token_str = tokenizer.decode(self.image_token_id)
return image_token_str * self.image_feature_size, image_token_str
def as_cli_args_dict(self) -> Dict[str, Any]:
"""Flatten vision language config to pure args.