amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8
11B • Updated • 5.55k
XuebinWang
XuebinWang
·
AI & ML interests
None yet
Recent Activity
new activity 8 days ago
amd/MiniMax-M2.1-MXFP4:Mismatch model shape new activity about 1 month ago
amd/gpt-oss-20b-WFP8-AFP8-KVFP8:Amd R9700 - vLLM crashes on startup published a model about 2 months ago
amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8Organizations
Mismatch model shape
10
#1 opened about 2 months ago
by 
twinsen123
Amd R9700 - vLLM crashes on startup
2
#6 opened about 1 month ago
by 
jmander11
published 2
models about 2 months ago
update readme
#5 opened 2 months ago
by 
XuebinWang
Update models and readme with accuracy number and disclaimer
#7 opened 2 months ago
by XuebinWang
update readme with disclaimer
#4 opened 2 months ago
by XuebinWang
update readme
#3 opened 3 months ago
by XuebinWang
update README (results etc) and upload LICENSE and USAGE_POLICY
#2 opened 3 months ago
by XuebinWang
Update README and upload original files
#6 opened 4 months ago
by XuebinWang
updated a
model 4 months ago
Use self_attn in config.json
#5 opened 4 months ago
by XuebinWang
KV cache quantization in FP8
#1 opened 5 months ago
by XuebinWang
Change to FP8 customized attention quantization, and update README
#4 opened 5 months ago
by XuebinWang
updated a
model 5 months ago
update model with several fixings
#5 opened 5 months ago
by XuebinWang
Update README (NOT ready to use)
#3 opened 5 months ago
by XuebinWang
Update README (NOT ready to use)
#3 opened 5 months ago
by XuebinWang
Update README
#2 opened 5 months ago
by XuebinWang
updated a
collection 5 months ago