msaroufim

awesome-profiling

Awesome utilities for performance profiling

mynotes

mlsys-experiments

stuff

metal-tutorial

tinyoptimizer

Triton-Puzzles

Puzzles for learning Triton

cpuoffload

setup

cpu-offload

algorithmic-efficiency

MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvements in both training algorithms and models.

axolotl

Go ahead and axolotl questions

gradient-checkpointing

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).

ImageBind

ImageBind One Embedding Space to Bind Them All

keras-benchmarks-2

lecturex

Liger-Kernel

Efficient Triton Kernels for LLM Training

lit-llama

Simple (fast) transformer inference in PyTorch with torch.compile + lit-llama code

llama-inference

experiments with inference on llama

llama2.c

Inference Llama 2 in one file of pure C

llm.c

LLM training in simple, raw C/CUDA

lm-evaluation-harness

A framework for few-shot evaluation of language models.

microbenchmarks

mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

newblog

new blog, who dis?

nvcc4jupyter

A plugin for Jupyter Notebook to run CUDA C/C++ code

pyperformance

Python Performance Benchmark Suite

pytorch.github.io

The website for PyTorch

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

subclass_zoo