CubicQuant: Parametric Non-Uniform Codebooks for High-Throughput LLM Inference with 1-8-Bit Weights
Paper • 2608.06763 • Published • 3
wwj
jaywanghz
AI & ML interests
None yet
Recent Activity
upvoted a paper about 12 hours ago
CubicQuant: Parametric Non-Uniform Codebooks for High-Throughput LLM Inference with 1-8-Bit Weights new activity over 2 years ago
Qwen/Qwen1.5-14B-Chat-GPTQ-Int4:can't run with fastchat cuda 12.1 new activity over 2 years ago
zai-org/cogvlm-chat-hf:Is the hf version the same as the biligual demo version in Chatglm.cn?Organizations
None yet
upvoted a paper about 12 hours ago
can't run with fastchat cuda 12.1
2
#1 opened over 2 years ago
by jaywanghz
Is the hf version the same as the biligual demo version in Chatglm.cn?
2
#1 opened over 2 years ago
by jaywanghz
3060 12g demo代码可以跑起来 4090 24g内存溢出
6
#12 opened about 3 years ago
by 
duketxl