Petals Team

non-profit

https://petals.dev

Activity Feed Request to join this org

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 11 months ago

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

poedator authored a paper 11 months ago

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

View all activity

petals-team's activity

poedator

authored a paper 7 months ago

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

Paper • 2406.02532 • Published Jun 4, 2024 • 13

poedator

authored 2 papers 11 months ago

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

Paper • 2306.03078 • Published Jun 5, 2023 • 3

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

Paper • 2402.12374 • Published Feb 19, 2024 • 3

borzunov

authored a paper about 1 year ago

Distributed Inference and Fine-tuning of Large Language Models Over The Internet

Paper • 2312.08361 • Published Dec 13, 2023 • 25

borzunov

updated 2 models over 1 year ago

petals-team/falcon-rw-1b

Text Generation • Updated Sep 3, 2023 • 19 • 2

petals-team/StableBeluga2

Text Generation • Updated Aug 23, 2023 • 1.51M • 19