A high-throughput and memory-efficient inference and serving engine for LLMs

Dynamic Instrumentation Tool Platform

Portable C and C++ Development Kit for x64 (and x86) Windows

Design patterns implemented in Java

Model interpretability and understanding for PyTorch

Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight), https://openreview.net/forum?id=JePfAI8fah

🔍 A Hex Editor for Reverse Engineers, Programmers and people who value their retinas when working at 3 AM.

code and discussion of a counter_based_engine for the C++ standard

3D Maps for OpenSceneGraph / C++14

Example models using DeepSpeed

C++ standards drafts

YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

NCCL Tests

Inference Llama 2 in one file of pure C

LLM training in simple, raw C/CUDA

ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale

Automating Web Performance testing with Puppeteer 🎪

Convert C++ header files to PlantUML

MIRROR of the SimGrid framework, for the simulation of distributed applications (Clouds, HPC, Grids, IoT and others). Most of the dev occurs on FramaGit.

Implementation of C++ standard libraries in C

🔥 A Complete List of GitHub Profile Badges and Achievements 🔥

AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)

Machine Learning Resources, Practice and Research

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch

Inference code for Llama models