FasterDecoding

community

https://github.com/FasterDecoding

Activity Feed Request to join this org

AI & ML interests

Making model inference more efficient by model-system codesign.

Recent Activity

tianlecai authored a paper 8 months ago

SnapKV: LLM Knows What You are Looking for Before Generation

tianlecai authored a paper 8 months ago

JetMoE: Reaching Llama2 Performance with 0.1M Dollars

Gsunshine authored a paper 10 months ago

One-Step Diffusion Distillation via Deep Equilibrium Models

View all activity

Organization Card

Community About org cards

Think deeper, decode faster

models 8

FasterDecoding/BitDelta_Mistral_combo

FasterDecoding/medusa-1.0-vicuna-13b-v1.5

Text Generation • Updated Jan 25 • 18 • 1

FasterDecoding/medusa-1.0-vicuna-33b-v1.3

Text Generation • Updated Dec 18, 2023 • 16

FasterDecoding/medusa-1.0-zephyr-7b-beta

Text Generation • Updated Dec 18, 2023 • 424 • 1

FasterDecoding/medusa-v1.0-vicuna-7b-v1.5

Text Generation • Updated Oct 29, 2023 • 653

FasterDecoding/medusa-vicuna-33b-v1.3

Updated Sep 11, 2023 • 50 • 4

FasterDecoding/medusa-vicuna-13b-v1.3

Updated Sep 11, 2023 • 150 • 5

FasterDecoding/medusa-vicuna-7b-v1.3

Updated Sep 11, 2023 • 8.24k • 16

datasets

None public yet