Li Xingjian (char-1ee)

char-1ee

Geek Repo

Company:Nanyang Technological University

Location:Singapore

Twitter:@lix1ngjian

Github PK Tool:Github PK Tool

Li Xingjian's starred repositories

Stargazers:280Issues:0Issues:0

OpenDiT

OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference

Language:PythonLicense:Apache-2.0Stargazers:1224Issues:0Issues:0

cudf

cuDF - GPU DataFrame Library

Language:C++License:Apache-2.0Stargazers:7986Issues:0Issues:0

duckdb

DuckDB is an analytical in-process SQL database management system

Language:C++License:MITStargazers:20414Issues:0Issues:0

Serving

A flexible, high-performance carrier for machine learning models(『飞桨』服务化部署框架)

Language:C++License:Apache-2.0Stargazers:887Issues:0Issues:0

desktop

Replit Desktop App

Language:TypeScriptStargazers:108Issues:0Issues:0

tensorrtllm_backend

The Triton TensorRT-LLM Backend

Language:PythonLicense:Apache-2.0Stargazers:581Issues:0Issues:0

paddler

Stateful load balancer custom-tailored for llama.cpp

Language:GoLicense:MITStargazers:392Issues:0Issues:0

NPKit

NCCL Profiling Kit

Language:PythonLicense:MITStargazers:85Issues:0Issues:0

dlrover

DLRover: An Automatic Distributed Deep Learning System

Language:PythonLicense:NOASSERTIONStargazers:1055Issues:0Issues:0

DistServe

Disaggregated serving system for Large Language Models (LLMs).

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:119Issues:0Issues:0
Language:JavaScriptLicense:MITStargazers:493Issues:0Issues:0

inference

Reference implementations of MLPerf™ inference benchmarks

Language:PythonLicense:Apache-2.0Stargazers:1130Issues:0Issues:0

ThunderKittens

Tile primitives for speedy kernels

Language:CudaLicense:MITStargazers:1338Issues:0Issues:0

AFFiNE

There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable and ready to use.

Language:TypeScriptLicense:NOASSERTIONStargazers:35264Issues:0Issues:0

core

MoonBit's Core library

Language:ShellLicense:Apache-2.0Stargazers:464Issues:0Issues:0

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

License:MITStargazers:2812Issues:0Issues:0

Awesome-LLM-Inference

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

License:GPL-3.0Stargazers:1845Issues:0Issues:0

llm-scheduling-artifact

Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“

Language:PythonLicense:Apache-2.0Stargazers:37Issues:0Issues:0
Language:PythonLicense:MITStargazers:3958Issues:0Issues:0

llama3

The official Meta Llama 3 GitHub site

Language:PythonLicense:NOASSERTIONStargazers:22646Issues:0Issues:0

experiments

My exploration on new technologies.

Language:PythonLicense:MITStargazers:6Issues:0Issues:0

attorch

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

Language:PythonLicense:MITStargazers:412Issues:0Issues:0

xformers

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

Language:PythonLicense:NOASSERTIONStargazers:7960Issues:0Issues:0

AISystem

AISystem 主要是指AI系统,包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:9302Issues:0Issues:0

triton

Development repository for the Triton language and compiler

Language:C++License:MITStargazers:11834Issues:0Issues:0

attention_with_linear_biases

Code for the ALiBi method for transformer language models (ICLR 2022)

Language:PythonLicense:MITStargazers:489Issues:0Issues:0

llm.c

LLM training in simple, raw C/CUDA

Language:CudaLicense:MITStargazers:21255Issues:0Issues:0

public-apis

A collective list of free APIs

Language:PythonLicense:MITStargazers:297114Issues:0Issues:0

mistral-inference

Official inference library for Mistral models

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:9120Issues:0Issues:0