Rust bindings for the Python interpreter

程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).

Perplexity open source garden for inference technology

Yet Another Document Translator

Fil-C: completely compatible memory safety for C and C++

⚡ Clash for Lab 是为实验室环境设计的科学上网工具，无需sudo权限，优雅地一键式脚本安装

程序员延寿指南 | A programmer's guide to live longer

A Throughput-Optimized Pipeline Parallel Inference System for Large Language Models

Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

DeepEP: an efficient expert-parallel communication library

Practical GPU Sharing Without Memory Size Constraints

Optimized primitives for collective multi-GPU communication

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

ArcticInference: vLLM plugin for high-throughput, low-latency inference

技术面试最后反问面试官的话

Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

A lightweight design for computation-communication overlap.

Python bindings for UCX

Tile primitives for speedy kernels

Perplexity GPU Kernels

Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)

NVIDIA Inference Xfer Library (NIXL)

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton

A fast communication-overlapping library for tensor/expert parallelism on GPUs.

A Datacenter Scale Distributed Inference Serving Framework

Development repository for the Triton language and compiler