Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
Paper • 2309.05516 • Published • 12
He, Xin
xinhe
AI & ML interests
None yet
Recent Activity
updated a model 1 day ago
INCModel/Qwen3-0.6B-MXFP4-MXFP8 published a model 1 day ago
INCModel/Qwen3-0.6B-MXFP4-MXFP8 updated a model 14 days ago
Intel/DeepSeek-V4-Pro-W4A16-AutoRoundOrganizations
authored a
paper over 2 years ago