支持大麦网，淘票票、缤玩岛等多个平台，演唱会演出抢票脚本

NVIDIA Inference Xfer Library (NIXL)

DeepEP: an efficient expert-parallel communication library

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

Minimalist ML framework for Rust

Ongoing research training transformer models at scale

This is a text generation method which returns a generator, streaming out each token in real-time during inference, based on Huggingface/Transformers.

Large Language Model Text Generation Inference

Intel PMU profiling tools

A proxy for code-server

A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.

Language-agnostic persistent background job server

Writing an OS in Rust

一个可以快速导出、查看你的微信聊天记录的工具

A GPU performance profiling tool for PyTorch models

📖 作为对《CMake Cookbook》的中文翻译。

Please visit https://github.com/IBM/pytorch-large-model-support for the latest information on PyTorch LMS.

YAML for command line

北京市预约挂号统一平台挂号小助手

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Minimal PyPI server for uploading & downloading packages with pip/easy_install

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

Implementation of https://arxiv.org/abs/1904.00962

Tutorial code on how to build your own Deep Learning System in 2k Lines

TestDisk & PhotoRec

SPlayerX@2018

🧠 Laws, Theories, Principles and Patterns for developers and technologists.

[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl

Patterns and behaviors for GPU computing

Repo for counting stars and contributing. Press F to pay respect to glorious developers.