AlphaUncommon
AI-Hypercomputer/JetStream
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
- Owner
- AI-Hypercomputer (organization)
- Stars
- Stars: 472
- Forks
- Forks: 70
- Language
- Python
- License
- Apache-2.0
- Created
- 2024
- Topics
- gemmagptgpuinferencejaxlarge-language-modelsllamallama2llmmodel-serving
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by AI-Hypercomputer
All 8 repos by AI-Hypercomputer- AI-Hypercomputer/maxtextStars: 2,455PythonRC
- AI-Hypercomputer/maxdiffusionStars: 393PythonAlpha
- AI-Hypercomputer/RecMLStars: 230PythonPrototype
- AI-Hypercomputer/xpkStars: 196PythonPrototype
- AI-Hypercomputer/gpu-recipesStars: 144PythonPrototype
- AI-Hypercomputer/tpu-recipesStars: 136ShellPrototype
Nearby in Python
All Python repos- huskydoge/Awesome-Loop-ModelsStars: 472PythonAlpha
- tizzy916/humanities-writing-companionStars: 472PythonAlpha
- AI272/speakerStars: 472PythonAlpha
- tildaslash/RatticWebStars: 472PythonAlpha
- xbmc-adult/xbmc-adultStars: 472PythonAlpha
- Gifts/Rogue-MySql-ServerStars: 472PythonAlpha