Minimalistic large language model 3D-parallelism training

Inference code for Llama models

llama3 implementation one matrix multiplication at a time

NVIDIA GPUDirect Storage Driver

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

grep for words with similar meaning to the query

A simple, high-throughput file client for mounting an Amazon S3 bucket as a local file system.

Implementation of a new caching algo called SIEVE. Link to paper included in README

SIEVE Cache for Crystal lang

implement SIEVE cache eviction algorithm

Cache implementation in ABAP

Retrieval and Retrieval-augmented LLMs

A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.

Speed up fsspec data access with Alluxio distributed caching.

Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.

A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems

Major CS conference publication stats (including accepted and submitted) by year.

A tool for measuring energy consumption of Intel CPUs

The hub for EleutherAI's work on interpretability and learning dynamics

Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"

Send email in Python conveniently for gmail using yagmail

A dump of some of our Presto logs, for use as part of ongoing Presto/HDFS research and presentations.

Performance Optimizer Observation Platform

A SIEVE cache implementation for D

A SIEVE cache implementation for C++

Java implementation of the S3 Fifo Cache

Disaggregated serving system for Large Language Models (LLMs).

Inference Llama 2 in one file of pure C

Llama2 transformer walkthrough with code examples