宋小猫

SongXiaoMao's activity

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

New activity in nerkyor/Qwen3.6-27B-DSV4Pro-Thinking-Distill 5 days ago

VLLM启动报错

9

#2 opened 6 days ago by

SongXiaoMao

New activity in havenoammo/Qwen3.6-27B-INT8-MTP about 1 month ago

MTP efficiency without official FP8 ha

👍 1

#1 opened about 1 month ago by

SongXiaoMao

New activity in nameistoken/Qwen3.6-27B-Quark-W8A8-INT8 about 1 month ago

MTP cannot be accelerated

#1 opened about 1 month ago by

SongXiaoMao

New activity in inclusionAI/Ling-2.6-flash-int4 2 months ago

The official VLLM example starts normal inference error

#3 opened 2 months ago by

SongXiaoMao

New activity in groxaxo/Qwen3.6-27B-GPTQ-Pro-4bit 2 months ago

This model cannot use MTP

4

#2 opened 2 months ago by

SongXiaoMao

Modify the configuration file

🔥 1

1

#1 opened 2 months ago by

SongXiaoMao

New activity in z-lab/Qwen3.5-27B-DFlash 3 months ago

FP8 work for base model or is 16-bit of 27B required?

17

#2 opened 3 months ago by

unoid

New activity in Jackrong/Qwopus3.5-27B-v3 3 months ago

Is there anyone who can tell me how to run this model with vllm correctly?

😔 3

7

#8 opened 3 months ago by

beginor

New activity in olka-fi/Qwen3.5-27B-MXFP4 3 months ago

Can the big guy quantify this model into MXFP4? Thank you!!

#3 opened 3 months ago by

SongXiaoMao

New activity in Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled 3 months ago

How does the VLLM start this model?

2

#4 opened 3 months ago by

SongXiaoMao

New activity in olka-fi/Qwen3.5-122B-A10B-MXFP4 3 months ago

This quantization model is amzing

❤️👍 2

5

#1 opened 4 months ago by

hyunw55

New activity in olka-fi/Qwen3.5-27B-MXFP4 3 months ago

Why is the file size of 4bit similar to FP8?

3

#2 opened 3 months ago by

SongXiaoMao

New activity in edp1096/Huihui-Qwen3.5-27B-abliterated-FP8 3 months ago

Sensitive information is not a question

2

#3 opened 3 months ago by

SongXiaoMao

New activity in win10/Huihui-Qwen3.5-27B-abliterated-FP8 3 months ago

VLLM 0.18.0 runs with an error

#2 opened 3 months ago by

SongXiaoMao

New activity in groxaxo/Huihui-Qwen3.5-27B-W8A8-INT8 3 months ago

I get an error using vllm0.18.0

1

#1 opened 3 months ago by

SongXiaoMao

New activity in huihui-ai/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated 3 months ago

使用VLLM启动会报错

#3 opened 3 months ago by

SongXiaoMao

New activity in Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled 3 months ago

Tokenizer class TokenizersBackend does not exist in vllm v0.17.1

12

#26 opened 4 months ago by

putcn

New activity in huihui-ai/Huihui-Qwen3.5-122B-A10B-abliterated-GGUF 4 months ago

Can you make a quantitative model? Qwen3.5-122B-A10B-GPTQ-Int4

#2 opened 4 months ago by

SongXiaoMao

New activity in Qwen/QwQ-32B over 1 year ago

When will you fix the model replies missing</think>\n start tags

18

#19 opened over 1 year ago by

xldistance

When answering questions in Chinese, the model frequently terminates prematurely (outputs the end token). Is this a common problem?

1

#40 opened over 1 year ago by

zhangw355