FasterDecoding/Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Jupyter NotebookApache-2.0
Watchers
- AlohaDollCoffee & Code Shop
- aweklingBitMain
- binhtranmcs
- brataoEscavador
- Chriss54
- CloseGoingAwayTetra LTD
- coder-drinker翼悟科技
- corranmac
- eemailme
- FarmingTongMindShare
- ghchris2021
- GsunshineCMU
- haim-barad@intel
- Henry-AveryShanghai
- huyuan-cn
- jnulzlGuangZhou China
- jtsai-quid@netbasequid
- junphine
- leeyeehooBurger Shot
- liujunchengSiliconFlow
- luluchouSichuan University
- N0wwaOrganization Strategy
- paramedickParameters Lab
- QubitiumModelCloud.ai
- songkq
- SpicygumL上海
- SynthpX
- VetreskaYandex
- vgoklaniNew York, NY
- WinDB3llState Ltd.
- yotamnahum@Samplead
- ZioZiaCapstone Inc.