用VLLM框架部署千问1.5并进行流式输出

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Video-Infinity generates long videos quickly using multiple GPUs without extra training.

2024机场推荐

CMake中文实战教程

flash attention tutorial written in python, triton, cuda, cutlass

amdgpu example code in hip/asm

LLM inference in C/C++

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

Making large AI models cheaper, faster and more accessible

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

汇总各大互联网公司容易考察的高频leetcode题🔥

how to optimize some algorithm in cuda.

Fast and memory-efficient exact attention

TinySTL is a subset of STL(cut some containers and algorithms) and also a superset of STL(add some other containers and algorithms)

Achieve a tiny STL in C++11

AKG (Auto Kernel Generator) is an optimizer for operators in Deep Learning Networks, which provides the ability to automatically fuse ops with specific patterns.

Compiler for Neural Network hardware accelerators

A domain specific language to express machine learning workloads.

PlaidML is a framework for making deep learning work everywhere.

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

Awesome resources for GPUs

Development repository for the Triton language and compiler

examples for tvm schedule API

The friendly PIL fork

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

Assembler for NVIDIA Volta and Turing GPUs

[ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl