Lists (20)
Stars
A collection of tricks and tools to speed up transformer models
A repo lists papers related to LLM based agent
Collection of various algorithms in mathematics, machine learning, computer science and physics implemented in C++ for educational purposes.
All Algorithms implemented in Python
A curated list of awesome Haskell frameworks, libraries and software.
A curated list of awesome C++ (or C) frameworks, libraries, resources, and shiny things. Inspired by awesome-... stuff.
An opinionated list of awesome Python frameworks, libraries, software and resources.
A curated list of Rust code and resources.
🦀 A curated list of Rust tools, libraries, and frameworks for working with LLMs, GPT, AI
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
Running large language models on a single GPU for throughput-oriented scenarios.
Transformer related optimization, including BERT, GPT
Fast inference from large lauguage models via speculative decoding
Landmark Attention: Random-Access Infinite Context Length for Transformers
Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.
SpotServe: Serving Generative Large Language Models on Preemptible Instances
Ongoing research training transformer models at scale
Disaggregated serving system for Large Language Models (LLMs).
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
FlashMLA: Efficient MLA decoding kernels
A plugin for Jupyter Notebook to run CUDA C/C++ code