nebuly-ai/optimate
A collection of libraries to optimise AI model performances
Provides specialized optimization libraries: Speedster applies hardware-aware compilation and quantization techniques to reduce inference latency, while ChatLLaMA optimizes LLM fine-tuning through RLHF alignment. Targets PyTorch and ONNX models deployed on GPUs/CPUs, with separate Kubernetes-focused tooling for dynamic resource partitioning. **Note: Project is in legacy status and no longer actively maintained.**
8,349 stars. No commits in the last 6 months.
Stars
8,349
Forks
624
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/nebuly-ai/optimate"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Tencent/AngelSlim
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
liyucheng09/Selective_Context
Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40%...
kyo-takano/chinchilla
A toolkit for scaling law research ⚖
antgroup/glake
GLake: optimizing GPU memory management and IO transmission.
microsoft/only_train_once
OTOv1-v3, NeurIPS, ICLR, TMLR, DNN Training, Compression, Structured Pruning, Erasing Operators,...