Philippe Bich's picture

2 4 12

Philippe Bich

pbicho

·

AI & ML interests

GenAI optimization, Quantization, Compression

Recent Activity

commented on a paper 9 days ago

SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights

upvoted a collection 10 days ago

new activity 11 days ago

huawei-csl/Qwen3-14B-3bit-SINQ:Update sample code to load from the correct repo (huawei-csl instead of huawei-cls)

View all activity

Organizations

upvoted a collection 10 days ago

SINQ

This collection contains the models quantized with the SINQ quantization method. • 13 items • Updated about 10 hours ago • 10

upvoted a paper 23 days ago

AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs

Paper • 2505.11557 • Published May 15 • 8

upvoted a paper 26 days ago

AcceLLM: Accelerating LLM Inference using Redundancy for Load Balancing and Data Locality

Paper • 2411.05555 • Published Nov 8, 2024 • 6

upvoted a paper 28 days ago

SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights

Paper • 2509.22944 • Published Sep 26 • 76