Starred repositories
A reading path for CPU performance engineering, from one instruction to production inference. Primary sources only, with a runnable benchmark for every section.
A syntax-highlighting interface for git, diff, blame, and grep/ripgrep
练习下用pytorch来复现下经典的推荐系统模型, 如MF, FM, DeepConn, MMOE, PLE, DeepFM, NFM, DCN, AFM, AutoInt, ONN, FiBiNET, DCN-v2, AFN, DCAP等
A file explorer tree for neovim written in lua
MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.
My learning notes for ML SYS.
Code, labs, and resources for O'Reilly AI Systems Performance Engineering: GPU optimization, distributed training, inference scaling, and full-stack tuning.
Classic papers and resources on recommendation
zero-peak / ZeroOmega
Forked from FelisCatus/SwitchyOmegaManage and switch between multiple proxies quickly & easily.
小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 | 评论爬虫、微博帖子 | 评论爬虫、百度贴吧帖子 | 百度贴吧评论回复爬虫 | 知乎问答文章|评论爬虫
DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.
State-of-the-art LLM compression, built for production inference with vLLM
Comprehensive collection of programming styles using a simple computational task, term frequency
The book "Performance Analysis and Tuning on Modern CPU"
Collaborative Collection of C++ Best Practices. This online resource is part of Jason Turner's collection of C++ Best Practices resources. See README.md for more information.
D2 is a modern diagram scripting language that turns text to diagrams.
该仓库尝试整理推荐系统领域的一些经典算法模型
A CPU tool for benchmarking the peak of floating points
Easy-to-use,Modular and Extendible package of deep-learning based CTR models .
A blazing fast inference solution for text embeddings models
A simple deep learning framework in pure python for purpose of learning in DL
An annotated implementation of the Transformer paper.
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
A high-throughput and memory-efficient inference and serving engine for LLMs
[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.
💥 A Lodash-style Go library based on Go 1.18+ Generics (map, filter, contains, find...)