chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[GLM-OCR] Support GLM-OCR Model (#17582)

Browse Source 
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
This commit is contained in:
Yuxuan Zhang
2026-01-27 14:24:00 +08:00
committed by GitHub
parent 81c0f5c5ad
commit 7106f6c8e1
9 changed files with 679 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
python/sglang/srt/multimodal/processors/glm4v.py
View File

@@ -3,6 +3,7 @@ from typing import List, Union
from sglang.srt.layers.rotary_embedding import MRotaryEmbedding
from sglang.srt.models.glm4v import Glm4vForConditionalGeneration
from sglang.srt.models.glm4v_moe import Glm4vMoeForConditionalGeneration
from sglang.srt.models.glm_ocr import GlmOcrForConditionalGeneration
from sglang.srt.multimodal.processors.base_processor import (
BaseMultimodalProcessor as SGLangBaseProcessor,
)
@@ -10,7 +11,11 @@ from sglang.srt.multimodal.processors.base_processor import MultimodalSpecialTok
class Glm4vImageProcessor(SGLangBaseProcessor):
models = [Glm4vForConditionalGeneration, Glm4vMoeForConditionalGeneration]
models = [
Glm4vForConditionalGeneration,
Glm4vMoeForConditionalGeneration,
GlmOcrForConditionalGeneration,
]
def __init__(self, hf_config, server_args, _processor, *args, **kwargs):
super().__init__(hf_config, server_args, _processor, *args, **kwargs)