XuebinWang

XuebinWang's activity

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

New activity in amd/gpt-oss-20b-WFP8-AFP8-KVFP8 1 day ago

Amd R9700 - vLLM crashes on startup

2

#6 opened 3 days ago by

jmander11

published 2 models 16 days ago

amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8

11B • Updated 22 days ago • 68

amd/gpt-oss-20b-WFP8-AFP8-KVFP8

21B • Updated 22 days ago • 71

New activity in amd/gpt-oss-20b-WFP8-AFP8-KVFP8 22 days ago

update readme

#5 opened 22 days ago by

XuebinWang

New activity in amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8 22 days ago

Update models and readme with accuracy number and disclaimer

#7 opened 22 days ago by

XuebinWang

New activity in amd/gpt-oss-20b-WFP8-AFP8-KVFP8 22 days ago

update readme with disclaimer

#4 opened 22 days ago by

XuebinWang

New activity in amd/gpt-oss-20b-WFP8-AFP8-KVFP8 about 1 month ago

update readme

#3 opened about 1 month ago by

XuebinWang

update README (results etc) and upload LICENSE and USAGE_POLICY

#2 opened about 1 month ago by

XuebinWang

New activity in amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8 3 months ago

Update README and upload original files

#6 opened 3 months ago by

XuebinWang

updated a model 3 months ago

amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8

11B • Updated 22 days ago • 68

New activity in amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8 3 months ago

Use self_attn in config.json

#5 opened 3 months ago by

XuebinWang

New activity in amd/gpt-oss-20b-WFP8-AFP8-KVFP8 3 months ago

KV cache quantization in FP8

#1 opened 3 months ago by

XuebinWang

New activity in amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8 3 months ago

Change to FP8 customized attention quantization, and update README

#4 opened 3 months ago by

XuebinWang

updated a model 3 months ago

amd/Mixtral-8x7B-Instruct-v0.1-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8

37B • Updated Nov 3, 2025 • 1

New activity in amd/Mixtral-8x7B-Instruct-v0.1-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8 3 months ago

update model with several fixings

#5 opened 3 months ago by

XuebinWang

New activity in amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8 3 months ago

Update README (NOT ready to use)

#3 opened 3 months ago by

XuebinWang

Update README

#2 opened 3 months ago by

XuebinWang

updated a collection 3 months ago

Quark Quantized Auto Mixed Precision (AMP) Models

Collection

7 items • Updated Dec 5, 2025 • 3

New activity in amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8 3 months ago

Initial commit to be used in vllm PR#27334

#1 opened 3 months ago by

XuebinWang

Initial commit to be used in vllm PR#27334

#1 opened 3 months ago by

XuebinWang