WEI

WEISHU's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in OpenGVLab/InternVL3_5-1B-Flash 1 day ago

It appears that the Flash series models are not compatible with the vLLM framework for inference.

#1 opened 1 day ago by

WEISHU

New activity in Qwen/Qwen3.5-0.8B 8 days ago

0.8B with mtp is slower than without mtp

#15 opened 8 days ago by

WEISHU

New activity in Qwen/Qwen3.5-0.8B 10 days ago

When vllm deployment is started using mtp config, an error will be reported. Please help！

2

#13 opened 14 days ago by

WEISHU

New activity in baidu/Qianfan-OCR 17 days ago

What are the correct versions of transformers and vllm?

4

#8 opened 26 days ago by

WEISHU

liked a model 10 months ago

opendatalab/MinerU2.0-2505-0.9B

1B • Updated Jun 12, 2025 • 84 • 41

liked a model 11 months ago

ByteDance/Dolphin

Image-Text-to-Text • Updated Jul 16, 2025 • 412 • 515

liked a model over 2 years ago

Norm/nougat-latex-base

Image-to-Text • 0.3B • Updated Feb 26, 2024 • 3.61k • 82