xingjinglu

xingjinglu's Stars

• michaelfeil/infinity

  Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

  Language:Python1.5k116

• sgl-project/sgl-learning-materials

  Materials for learning SGLang

  1187

• LyWangPX/Reinforcement-Learning-2nd-Edition-by-Sutton-Exercise-Solutions

  Solutions of Reinforcement Learning, An Introduction

  Language:Jupyter Notebook2k465

• hijkzzz/Awesome-LLM-Strawberry

  A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

  5.4k296

• dottxt-ai/outlines

  Structured Text Generation

  Language:Python9.8k503

• flashinfer-ai/flashinfer

  FlashInfer: Kernel Library for LLM Serving

  Language:Cuda1.5k147

• skypilot-org/skypilot

  SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

  Language:Python6.8k516

• ShishirPatil/gorilla

  Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

  Language:Python11.5k1k

• kvcache-ai/ktransformers

  A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

  Language:Python75441

• pcg-mlp/KsanaLLM

  Language:C++29330

• pku-liang/MAGIS

  MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)

  Language:Python474

• mcrl/tccl

  Thunder Research Group's Collective Communication Library

  Language:C++263

• byungsoo-oh/ml-systems-papers

  Curated collection of papers in machine learning systems

  1749

• Yanz2015/architecture.wechat-tencent

  互联网公司架构: 微信技术架构， 腾讯技术架构

  1

• rohan-paul/LLM-FineTuning-Large-Language-Models

  LLM (Large Language Model) FineTuning

  Language:Jupyter Notebook471112

• hpcaitech/Open-Sora

  Open-Sora: Democratizing Efficient Video Production for All

  Language:Python22.4k2.2k

• lamini-ai/lamini

  The Official Python Client for Lamini's API

  Language:Python2.5k151

• PKU-YuanGroup/Open-Sora-Plan

  This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

  Language:Python11.6k1k

• comfyanonymous/ComfyUI

  The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

  Language:Python58.5k6.2k

• alibaba/rtp-llm

  RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

  Language:C++55050

• OpenPPL/ppl.nn

  A primitive library for neural network

  Language:C++1.3k217

• trailofbits/vast

  VAST is an experimental compiler pipeline designed for program analysis of C and C++. It provides a tower of IRs as MLIR dialects to choose the best fit representations for a program analysis or further program abstraction.

  Language:C++39924

• ELS-RD/kernl

  Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

  Language:Jupyter Notebook1.5k94

• BBuf/tvm_mlir_learn

  compiler learning resources collect.

  Language:Python2.2k332

• Lin-Mao/DrGPUM

  A memory profiler for NVIDIA GPUs to explore memory inefficiencies in GPU-accelerated applications.

  Language:Python222

• Jokeren/triton-samples

  Language:Jupyter Notebook231

• mlcommons/inference

  Reference implementations of MLPerf™ inference benchmarks

  Language:Python1.2k536

• mlcommons/training

  Reference implementations of MLPerf™ training benchmarks

  Language:Python1.6k561

• jmellorcrummey/cupti-test

  Test overhead of CUPTI PC sampling for CUDA 10

  Language:C++31

• ROCm/triton

  Development repository for the Triton language and compiler

  Language:C++9629