Void Main's starred repositories
alpaca-lora
Instruct-tune LLaMA on consumer hardware
open-gpu-kernel-modules
NVIDIA Linux open GPU kernel module source
flash-attention
Fast and memory-efficient exact attention
nn-zero-to-hero
Neural Networks: Zero to Hero
ML-Papers-of-the-Week
🔥Highlighting the top ML papers every week.
PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
awesome-langchain
😎 Awesome list of tools and projects with the awesome LangChain framework
DeepSpeedExamples
Example models using DeepSpeed
LookaheadDecoding
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
Awesome-LLM-Long-Context-Modeling
📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥
magvit2-pytorch
Implementation of MagViT2 Tokenizer in Pytorch
AI-Software-Startups
A Survey of AI startups
nccl-fastsocket
NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.