AlphaUncommon
vectorch-ai/ScaleLLM
A high-performance inference system for large language models, designed for production environments.
Archived: this repository is read-only
- Owner
- vectorch-ai (organization)
- Stars
- Stars: 498
- Forks
- Forks: 41
- Language
- C++
- License
- Apache-2.0
- Created
- 2023
- Topics
- cudainferencellmllm-inferencemodelproductionservingspeculativetransformerefficiency
- Tier
- Alpha (250 to 699 ★) What this tier means
Nearby in C++
All C++ repos- keenon/nimblephysicsStars: 498C++Alpha
- anysphere/gpt-4-for-codeStars: 498C++Alpha
- JMBQ01/azurlanStars: 498C++Alpha
- stxxl/stxxlStars: 498C++Alpha
- mariadb-corporation/galeraStars: 498C++Alpha
- MAPIRlab/rf2o_laser_odometryStars: 498C++Alpha