Ofir Zafrir

ofirzaf

·

AI & ML interests

Sparsity, Qunatization, Model Compression

Recent Activity

liked a model about 1 month ago

z-lab/Qwen3.6-35B-A3B-DFlash

upvoted an article about 1 month ago

Intel XPU Kernel Skill: LLM-driven Triton kernel optimization for the Hugging Face Kernel Hub

upvoted an article 5 months ago

Getting More from Your Test-Time Compute Budget with Portfolio Beam Search

View all activity

Organizations

authored 2 papers over 1 year ago

Q8BERT: Quantized 8Bit BERT

Paper • 1910.06188 • Published Oct 14, 2019 • 2

FastDraft: How to Train Your Draft

Paper • 2411.11055 • Published Nov 17, 2024 • 11

authored a paper about 3 years ago

An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs

Paper • 2306.16601 • Published Jun 28, 2023 • 4