msaroufim

lectures

Material for gpu-mode lectures

neurips_llm_efficiency_challenge

NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day

awesome-profiling

Awesome utilities for performance profiling

C-compiler-optimizations

Description of commonly done compiler optimizations in C

ml-design-patterns

Software Architecture for ML engineers

multiple_dispatch

Why multiple dispatch lets you write composable code

ao

PyTorch native quantization and sparsity for training and inference

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

serve

Serve, optimize and scale PyTorch models in production

msaroufim/awesome-profiling

Awesome utilities for performance profiling

msaroufim/mynotes

msaroufim/mlsys-experiments

stuff

msaroufim/metal-tutorial

msaroufim/tinyoptimizer

msaroufim/Triton-Puzzles

Puzzles for learning Triton

msaroufim/cpuoffload

msaroufim/setup

msaroufim/cpu-offload

msaroufim/ao

PyTorch native quantization and sparsity for training and inference

msaroufim/axolotl

Go ahead and axolotl questions

msaroufim/factorio-rl

msaroufim/gradient-checkpointing

msaroufim/helm

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

msaroufim/hqq

Official implementation of Half-Quadratic Quantization (HQQ)

msaroufim/keras-benchmarks-2

msaroufim/lecturex

msaroufim/Liger-Kernel

Efficient Triton Kernels for LLM Training

msaroufim/lit-llama

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

msaroufim/llm.c

LLM training in simple, raw C/CUDA

msaroufim/lm-evaluation-harness

A framework for few-shot evaluation of language models.

msaroufim/microbenchmarks

msaroufim/mlc-llm

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

msaroufim/newblog

new blog, who dis?

msaroufim/nvcc4jupyter

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

msaroufim/pyperformance

Python Performance Benchmark Suite

msaroufim/pytorch.github.io

The website for PyTorch

msaroufim/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.

msaroufim/subclass_zoo

msaroufim/yolo-save

yolo push a commit to remote when you save any file