wenhua cheng
wenhuach
AI & ML interests
Model Compression, CV
Recent Activity
new activity
about 14 hours ago
Intel/Qwen3-Next-80B-A3B-Thinking-int4-AutoRound:Qwen/Qwen3-Next-80B-A3B-Thinking has MMLU_PRO 82.7 but you guys get 0.7271
updated
a model
7 days ago
Intel/DeepSeek-V3.2-int4-AutoRound
updated
a model
8 days ago
Intel/GLM-4.7-Flash-int4-AutoRound
Organizations
Qwen/Qwen3-Next-80B-A3B-Thinking has MMLU_PRO 82.7 but you guys get 0.7271
3
#2 opened 4 months ago
by
hlxxxxxx
AutoRound request: GLM-4.5-Air
1
#1 opened 30 days ago
by
babytifa
2507 Thinking model release
11
#4 opened 4 months ago
by
anjeysapkovski
How to use this kernel
#1 opened about 1 month ago
by
wenhuach
Thinking version has been deleted?
1
#2 opened about 2 months ago
by
reswewr
Improve model card: Add pipeline tag, library name, and update paper/citation
🔥
1
#1 opened about 2 months ago
by
nielsr
Could we get more w2a16 w3a16 and w4a16 Autoround
👍
1
1
#1 opened 3 months ago
by
twhitworth
Practical performance feedback
1
#2 opened 3 months ago
by
maigonis
Works good with vLLM, just no tool calling
1
#1 opened 5 months ago
by
Ununnilium
Inference with llama.cpp + Open WebUI gives repeating `?`
4
#1 opened 3 months ago
by
whoisjeremylam
Adding `transformers` as the library tag
#3 opened 4 months ago
by
ariG23498
CPU only?
4
#2 opened 5 months ago
by
jujutechnology
Error loading in vLLm 10.1+
👍
1
2
#2 opened 5 months ago
by
freegheist
Could you please consider release a 2-bit GPTQ or AWQ model for vllm
3
#1 opened 5 months ago
by
kq
Bits for embedding / lm-head / non expert layers
1
#1 opened 6 months ago
by
sokann
Awesome Any Chance for this for GLM-4.5
2
#1 opened 6 months ago
by
Fernanda24
Whats the difference between this and autoround_v0?
7
#1 opened 6 months ago
by
pty819
auto-round
#482 opened 9 months ago
by
wenhuach
how to run this model
4
#1 opened 10 months ago
by
cicdatopea
Update README.md
#1 opened about 1 year ago
by
wenhuach