brian-pieces

llm.c

LLM training in simple, raw C/CUDA

mojo

The Mojo Programming Language

vllm-inference

benchmark_dart_javascript

dev-chatgpt-prompts

📚 Personal collection of ChatGPT prompts for developers!

LLM-SLERP-Merge

Spherical Merge Pytorch/HF format Language Models with minimal feature loss.

flutter_llama

llama.cpp bindings for Flutter

mlx-examples

Examples in the MLX framework

hydra-moe

axlearn

An Extensible Deep Learning Library

mlx

MLX: An array framework for Apple silicon

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

llama_walkthrough

Llama2 transformer walkthrough with code examples

llamafile

Distribute and run LLMs with a single file.

chatgpt_system_prompt

A collection of GPT system prompts and various prompt injection/leaking knowledge.

S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

tvm_mlir_learn

compiler learning resources collect.

llama.onnx

LLaMa/RWKV onnx models, quantization and testcase

teenygrad

If tinygrad wasn't small enough for you...

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

candle

Minimalist ML framework for Rust

docs

The documents for TVM Unity

mlsys-literature

A collection of papers related to machine learning systems. (still in early stage of collection)

neural-engine

Everything we actually know about the Apple Neural Engine (ANE)

tinygrad

You like pytorch? You like micrograd? You love tinygrad! ❤️

llama2.c

Inference Llama 2 in one file of pure C

mojograd

Implementation of Karpathy's micrograd in Mojo :fire:

mojodojo.dev

Learning materials for the Mojo🔥programming language

flutter_graph_view

An open source project which can display beautiful graph data structure, such as force-directed.

Awesome-DynamicGraphLearning

Awesome papers about machine learning (deep learning) on dynamic (temporal) graphs (networks / knowledge graphs).