LEI WANG

yiakwy-xpu-team's activity

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

New activity in sgl-project/DeepSeek-V4-Flash-FP8 11 days ago

请问这个FP8模型是怎么转换出来的?

3

#2 opened 27 days ago by

Paul1006

New activity in allenai/c4 3 months ago

Cannot load dataset from hf hub

14

#7 opened over 2 years ago by

at676

upvoted 2 articles 3 months ago

view article

Article

5 Things You Need to Know About Moonshot AI and Kimi K2, the New #1 model on the Hub

• 

fdaudens

•

Jul 15, 2025

• 25

view article

Article

Enabling Large Scale RLHF of GPTOSS with Megatron backend in VeRL

• 

yiakwy-xpu-team

•

Feb 10

• 6

published an article 3 months ago

view article

Article

Enabling Large Scale RLHF of GPTOSS with Megatron backend in VeRL

• 

yiakwy-xpu-team

•

Feb 10

• 6

New activity in HKUSTAudio/xcodec2 9 months ago

codec模型初始化部分参数无法正确初始化

4

#12 opened about 1 year ago by

Qianguo

[xcodec2 model mismatch]

➕ 1

3

#13 opened 11 months ago by

judy9710

commented on Welcome GPT OSS, the new open-source model family from OpenAI! 9 months ago

view reply

For whom is working sft GPT_OSS, I providing scripts to convert gpt-oss-bf16-sft backt mxfp4 from bf16 :
https://github.com/openai/gpt-oss/pull/108/files

upvoted an article 9 months ago

view article

Article

Welcome GPT OSS, the new open-source model family from OpenAI!

• 
• 
• +10

reach-vb, pcuenq, lewtun, clem, Rocketknight1, clefourrier, celinah, Wauplin, marcsun13, pagezyhf, ahadnagy, joaogante

•

Aug 5, 2025

• 513

published an article 10 months ago

view article

Article

Comprehensive Study of H800x104 DGX SuperPod Disaggregation Strategy in SGLang v0.4.8

• 

yiakwy-xpu-team

•

Jul 19, 2025

• 7

published an article about 1 year ago

view article

Article

Efficient MoE Align & Sort design in SGLang Fused MoE

• 

yiakwy-xpu-team

•

Mar 25, 2025

• 3

upvoted a paper about 2 years ago

SparQ Attention: Bandwidth-Efficient LLM Inference

Paper • 2312.04985 • Published Dec 8, 2023 • 40

New activity in google/gemma-7b about 2 years ago

Why the original GGUF is quite large ?

15

#11 opened about 2 years ago by

nopainkiller

commented a paper over 2 years ago

Mixtral of Experts

Paper • 2401.04088 • Published Jan 8, 2024 • 160 •

8

liked a model over 2 years ago

Skywork/Skywork-13B-base

Text Generation • Updated Nov 24, 2023 • 1.71k • 70