HandH1998

HandH1998's activity

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

New activity in meituan/DeepSeek-R1-Channel-INT8 about 7 hours ago

Update inference/bf16_cast_channel_int8.py

#10 opened about 7 hours ago by

HandH1998

Update config.json

#9 opened about 7 hours ago by

HandH1998

New activity in meituan/DeepSeek-R1-Block-INT8 about 7 hours ago

After deploying with the latest sglang, I found that the responses when calling the interface were chaotic.

4

#13 opened 9 days ago by

ShiningMaker

New activity in meituan/DeepSeek-R1-Block-INT8 6 days ago

是否有明确的sglang镜像版本推荐：）

1

#14 opened 6 days ago by

wangkkk956

New activity in meituan/DeepSeek-R1-Channel-INT8 6 days ago

Add `quantization_config` in config.json?

4

#4 opened 7 days ago by

WeiwenXia

运行channel INT8后sglang报错OOM

1

#3 opened 9 days ago by

zhangneilc

New activity in meituan/DeepSeek-R1-Block-INT8 10 days ago

量化类型

1

#11 opened 12 days ago by

a-r-c

New activity in meituan/DeepSeek-R1-Channel-INT8 13 days ago

Difference with Block-wise Int8?

1

#1 opened 14 days ago by

leo98xh

updated a model 13 days ago

meituan/DeepSeek-R1-Channel-INT8

Text Generation • Updated 13 days ago • 709 • 17

New activity in meituan/DeepSeek-R1-Channel-INT8 13 days ago

Update README.md

#2 opened 13 days ago by

HandH1998

New activity in meituan/DeepSeek-R1-Block-INT8 14 days ago

Why hasn't the model file size changed?

1

#9 opened 14 days ago by

yu5

updated a model 15 days ago

meituan/DeepSeek-R1-Block-INT8

Text Generation • Updated 13 days ago • 3.44k • 30

New activity in meituan/DeepSeek-R1-Block-INT8 15 days ago

Update README.md

#8 opened 15 days ago by

HandH1998

Update inference/bf16_cast_block_int8.py

#7 opened 15 days ago by

HandH1998

New activity in cognitivecomputations/DeepSeek-V3-AWQ 20 days ago

What calibration dataset do you use when applying AWQ?

2

#5 opened 27 days ago by

HandH1998

updated 2 models 8 months ago

HandH1998/QQQ-Llama-3-8b-g128

Text Generation • Updated Jul 17, 2024 • 1.24k • 1

HandH1998/QQQ-Llama-3-8b

Text Generation • Updated Jul 17, 2024 • 178