SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs
Paper
•
2512.04746
•
Published
•
9
wenhua cheng
wenhuach
AI & ML interests
Model Compression, CV
Recent Activity
reacted
to
their
post
with 🔥
about 6 hours ago
🚀 SignRoundV2 for LLM quantization: PTQ-level cost, QAT-level accuracy — yes, even at 2 bits.
https://huggingface.co/papers/2512.04746
new activity
about 7 hours ago
Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound:Improve model card: Add pipeline tag, library name, and update paper/citation
authored
a paper
2 days ago
SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs
Organizations
authored
a
paper
2 days ago