inkinworld

AI-RecommenderSystem

该仓库尝试整理推荐系统领域的一些经典算法模型

cpufp

A CPU tool for benchmarking the peak of floating points

DeepCTR

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

RecLearn

Recommender Learning with Tensorflow2.x

text-embeddings-inference

A blazing fast inference solution for text embeddings models

MatrixSlow

A simple deep learning framework in pure python for purpose of learning in DL

annotated-transformer

An annotated implementation of the Transformer paper.

marlin

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

vllm

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

llmperf

KIVI

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

pytriton

PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.

lo

💥 A Lodash-style Go library based on Go 1.18+ Generics (map, filter, contains, find...)

OpenHands

🙌 OpenHands: Code Less, Make More

CUDA-Programming-Guide-in-Chinese

This is a Chinese translation of the CUDA programming guide

sglang

SGLang is a fast serving framework for large language models and vision language models.

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Recommender-System

推荐系统综述

map

路书，路线规划，高德地图 api 示例，地图信息 vue3 ts vite

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

flog

:tophat: A fake log generator for common log formats

how-to-optim-algorithm-in-cuda

how to optimize some algorithm in cuda.

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.

The-Art-of-Linear-Algebra-zh-CN

Graphic notes on Gilbert Strang's "Linear Algebra for Everyone", 线性代数的艺术中文版, 欢迎PR.

llm-viz

3D Visualization of an GPT-style LLM

Nanbeige

CodeGeeX2

CodeGeeX2: A More Powerful Multilingual Code Generation Model

bcc

BCC - Tools for BPF-based Linux IO analysis, networking, monitoring, and more

cherry-markdown

✨ A Markdown Editor

text-generation-inference

Large Language Model Text Generation Inference