2 papers
cs.LG2026
BiLoCo: Binary Low-Rank Corrections for Post-Training Quantization
David Jin, Beshr IslamBouli, Tarushii Goel +2
Post-training quantization (PTQ) to FP4 has emerged as a key technique for reducing large language model inference cost, especially on Blackwell GPUs, which offer native FP4 tensor…
cs.LG2026
AAAC: Activation-Aware Adaptive Codebooks for 4-bit LLM Weight Quantization
Beshr IslamBouli, David Jin
Post-training weight-only quantization to 4 bits is widely used to reduce the memory and compute costs of large language model inference. Existing PTQ methods, such as AWQ and GPTQ…