Rust Code Review Guidelines , RCRG

Blazingly fast LLM inference.

Multilevel Optimized Matrix-matrix Multiplication Sandbox

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

A Hardware Description Language based on the Rust Programming Language

An attempt at achieving the theoretical best memory bandwidth of my machine.

C++11/14/17/20 Concurrency Demystified: From Core Principles to Thread-Safe Code

A handy ECS

Intel AVX-512简介

An APL-like programming language

🚀 Beat AI 简报: 持续分享 AI 领域的关键进展，帮你征服 AI，Just beat it! 欢迎 star 订阅.

Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.

Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search

A tiny library for coding with large language models.

A Python library transfers PyTorch tensors between CPU and NVMe

200行写一个自动微分工具

大模型多维度中文对齐评测基准 (ACL 2024)

Scalable Hashing on Persistent Memory

Cost/performance analysis of index structures on SSD and persistent memory (CIDR 2022)

DINOMO: An Elastic, Scalable, High-Performance Key-Value Store for Disaggregated Persistent Memory (PVLDB 2022, VLDB 2023)

RECIPE : high-performance, concurrent indexes for persistent memory (SOSP 2019)

Persistent Memory Development Kit

LLMPerf is a library for validating and benchmarking LLMs

High-performance, lock-free local and concurrent object memory pool with automated allocation, cleanup, and verification.

Prompt 编写模式：如何将思维框架赋予机器，以设计模式的形式来思考 prompt

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

fastest vector database made in numpy

Ongoing research training transformer models at scale

Efficient argmin & argmax

A fast llama2 decoder in pure Rust.