Petals Team

AI & ML interests

Running LLMs collaboratively

Recent Activity

poedator  authored a paper 7 months ago

SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices

poedator  authored a paper 10 months ago

SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

poedator  authored a paper 10 months ago

Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

View all activity

Team members 3