cr7258 / ai-infra-learningLinks
This repository organizes materials, recordings, and schedules related to AI-infra learning meetings.
☆317Updated this week
Alternatives and similar repositories for ai-infra-learning
Users that are interested in ai-infra-learning are comparing it to the libraries listed below
Sorting:
- 校招、秋招、春招、实习好项目,带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。☆491Updated 3 months ago
- 分享AI Infra知识&代码练习:PyTorch/vLLM/SGLang框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等☆215Updated this week
- learning how CUDA works☆373Updated 11 months ago
- 注释的nano_vllm仓库,并且完成了MiniCPM4的适配以及注册新模型的功能☆155Updated 5 months ago
- A self-learning tutorail for CUDA High Performance Programing.☆866Updated 3 weeks ago
- how to learn PyTorch and OneFlow☆481Updated last year
- CUDA 算子手撕与面试指南☆809Updated 5 months ago
- A light llama-like llm inference framework based on the triton kernel.☆169Updated 3 weeks ago
- The repository has collected a batch of noteworthy MLSys bloggers (Algorithms/Systems)☆317Updated last year
- UltraScale Playbook 中文版☆125Updated 10 months ago
- A CUDA tutorial to make people learn CUDA program from 0☆266Updated last year
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆114Updated 6 months ago
- ☆313Updated last year
- ☆40Updated 8 months ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆613Updated last month
- 高性能计算相关知识学习笔记,包含学习笔记和相关知识的代码demo,在持续完善中。 如果有帮助的话请Star一下,对作者帮助很大,谢谢!☆470Updated 2 years ago
- This repo is used for archiving my notes, codes and materials of cs learning.☆74Updated last week
- LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.☆859Updated last month
- 《CUDA编程基础与实践》一书的代码☆154Updated 3 years ago
- my cs notes☆57Updated last year
- 先进编译实验室的个人主页☆195Updated 3 months ago
- Codes & examples for "CUDA - From Correctness to Performance"☆121Updated last year
- 📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).☆63Updated 9 months ago
- vLLM Kunlun (vllm-kunlun) is a community-maintained hardware plugin designed to seamlessly run vLLM on the Kunlun XPU.☆239Updated last week
- ☆26Updated 5 months ago
- Flash Attention from Scratch on CUDA Ampere☆122Updated 5 months ago
- A tutorial for CUDA&PyTorch☆227Updated last week
- Code release for book "Efficient Training in PyTorch"☆125Updated 9 months ago
- Summary of some awesome work for optimizing LLM inference☆172Updated 2 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆772Updated 9 months ago