Feiyang Luo

iwaitu's activity

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

New activity in nvidia/Gemma-4-31B-IT-NVFP4 3 days ago

这个版本对于5090单卡来说还是太大了

10

#4 opened 7 days ago by

iwaitu

New activity in google/gemma-4-31B-it 3 days ago

Missing 'reasoning' field in response when serving gemma-4-31B-it with vLLM

8

#28 opened 5 days ago by

Iann

New activity in protoLabsAI/gemma-4-26B-A4B-it-FP8 7 days ago

it's the same size as FP16? (April 2nd 2026)

3

#1 opened 8 days ago by

wijjjj

New activity in HauhauCS/Qwen3.5-27B-Uncensored-HauhauCS-Aggressive 19 days ago

fp8 thx

1

#10 opened 22 days ago by

MRU4913

New activity in apolo13x/Qwen3.5-27B-NVFP4 19 days ago

Working well with vllm on 5090

❤️ 2

6

#1 opened about 1 month ago by

tiho64

New activity in apolo13x/Qwen3.5-27B-NVFP4 20 days ago

could you quantize this finetune model Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled

#3 opened 20 days ago by

iwaitu

New activity in Qwen/Qwen3-Next-80B-A3B-Thinking 7 months ago

FP8 版本无法使用vllm v0.10.2 来加载

#14 opened 7 months ago by

iwaitu

New activity in Qwen/Qwen3-235B-A22B 11 months ago

有用4张H20实践过的大佬吗

2

#10 opened 12 months ago by

Edison0902

New activity in zai-org/GLM-4-32B-0414 12 months ago

Need fp8 version for inerface

1

#2 opened 12 months ago by

iwaitu

New activity in unsloth/DeepSeek-R1-GGUF about 1 year ago

如何同时处理多个http请求

4

#27 opened about 1 year ago by

007hao

New activity in shenzhi-wang/Llama3.1-70B-Chinese-Chat over 1 year ago

有可能出一个70B的AWQ或者GPTQ-INT4的量化版本吗？

3

#4 opened over 1 year ago by

weiminw

请问有计划微调 Mistral Nemo 吗？

1

#3 opened over 1 year ago by

BB8-dev

New activity in shenzhi-wang/Llama3.1-8B-Chinese-Chat over 1 year ago

遇到了无穷回复问题

6

#4 opened over 1 year ago by

Orion-zhen