BLAS-like Library Instantiation Software Framework

Next generation BLAS implementation for ROCm platform

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!

Fast CUDA matrix multiplication from scratch

Step-by-step optimization of CUDA SGEMM

Source code for SIGMOD 2020 paper "Improving Approximate Nearest Neighbor Search through Learned Adaptive Early Termination"

[EMNLP 2023] Adapting Language Models to Compress Long Contexts

[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"

Python Packaging User Guide

CMake for C++ Best Practices

Collaborative Collection of C++ Best Practices. This online resource is part of Jason Turner's collection of C++ Best Practices resources. See README.md for more information.

An elegant \LaTeX\ résumé template. 大陆镜像 https://gods.coding.net/p/resume/git

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

Dumpy: A Compact and Adaptive Index for Large Data Series Collections (SIGMOD'23)

Open-source vector similarity search for Postgres

LLM inference in C/C++

Seed guided neural metric learning approach for calculating trajectory similarities

Hackable and optimized Transformers building blocks, supporting a composable construction.

Running large language models on a single GPU for throughput-oriented scenarios.

Learning to Compress Prompts with Gist Tokens - https://arxiv.org/abs/2304.08467

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

Examples from Programming in Parallel with CUDA

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Running inference on the ZeroSCROLLS benchmark

Official repository for LongChat and LongEval

Unsupervised text tokenizer for Neural Network-based text generation.

StableLM: Stability AI Language Models

A toolkit for machine learning from time series