FasterDecoding/Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Jupyter NotebookPythonShell
This is stars and forks stats for /FasterDecoding/Medusa repository. As of 22 Apr, 2024 this repository has 990 stars and 51 forks.

 Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads | Blog | Roadmap | News 🔥 [2023/09] Medusa won the Chai Prize Grant🎉 The prize will be used as a development bounty for those who help us achieve milestones in our roadmap! [2023/09] Medusa v0.1 is released! Introduction Medusa is a simple framework that democratizes the acceleration techniques for LLM generation with multiple decoding heads. Medusa on Vicuna-7b. We aim to tackle the three...
Read on GithubGithub Stats Page
repotechsstarsweeklyforksweekly
pnnl/neuromancerPythonCudaC++448+2760+1
Ptechgithub/ReverseTlsTunnelShell124+131+1
fscarmen2/Choreo2ShellDockerfile70340
No-Trade-No-Life/YuanTypeScriptDockerfileJavaScript2020180
eosnetworkfoundation/eos-evm-nodeCMakeC++Python0000
tairov/llama2.mojoPythonDockerfile1.2k0750
sismics/docker-apache2DockerfileShell9040+5
turboderp/exllamav2PythonCudaC++1.4k0740
ZiwenZhuang/parkourPython2450370
hyperledger-labs/open-enterprise-agentScalaKotlinJupyter Notebook24+130