Move mem_fraction_static adjustment for multimodal models to server_args.py & Fix session control & Other cleanups (#7748)

This commit is contained in:
Lianmin Zheng
2025-07-04 16:33:33 -07:00
committed by GitHub
parent 975a5ec69c
commit 14229ccf8f
16 changed files with 339 additions and 137 deletions

View File

@@ -3,11 +3,9 @@ import math
import re
from typing import Dict, List, Union
import torch
from PIL import Image
from sglang.srt.layers.rotary_embedding import MRotaryEmbedding
from sglang.srt.managers.schedule_batch import Modality, MultimodalDataItem
from sglang.srt.models.qwen2_5_vl import Qwen2_5_VLForConditionalGeneration
from sglang.srt.models.qwen2_vl import Qwen2VLForConditionalGeneration
from sglang.srt.multimodal.processors.base_processor import (