PrototypeCommon
toyaix/tritonllm
LLM Inference via Triton (Flexible & Modular): Focused on Kernel Optimization using CUBIN binaries, Starting from gpt-oss Model
Archived: this repository is read-only
- Owner
- toyaix (organization)
- Stars
- Stars: 119
- Forks
- Forks: 6
- Language
- Python
- License
- MIT
- Created
- 2025
- Topics
- tritoninferai-infrallm
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by toyaix
All 2 repos by toyaix- toyaix/triton-runnerStars: 100PythonPrototype
Nearby in Python
All Python repos- BaoZ-XHG/MaiMen-SaverStars: 119PythonPrototype
- tian1326/mcd-coupon-assistantStars: 119PythonPrototype
- divagr18/QwenPUStars: 119PythonPrototype
- rnk/django-media-bundlerStars: 119PythonPrototype
- pnegre/python-whiteboardStars: 119PythonPrototype
- powdahound/redis-collectd-pluginStars: 119PythonPrototype