ForceInjection / AI-fundermentalsLinks
AI 基础知识 - GPU 架构、CUDA 编程、大模型基础及AI Agent 相关知识
☆234Updated last week
Alternatives and similar repositories for AI-fundermentals
Users that are interested in AI-fundermentals are comparing it to the libraries listed below
Sorting:
- This repository organizes materials, recordings, and schedules related to AI-infra learning meetings.☆115Updated 3 weeks ago
- GLake: optimizing GPU memory management and IO transmission.☆473Updated 5 months ago
- A self-learning tutorail for CUDA High Performance Programing.☆712Updated last month
- 一种任务级GPU算力分时调度的高性能深度学习训练平台☆691Updated last year
- ☆483Updated 2 weeks ago
- Efficient and easy multi-instance LLM serving☆468Updated this week
- LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.☆812Updated this week
- Materials for learning SGLang☆530Updated last month
- KV cache store for distributed LLM inference☆311Updated 2 months ago
- Community maintained hardware plugin for vLLM on Ascend☆1,022Updated this week
- how to learn PyTorch and OneFlow☆449Updated last year
- UltraScale Playbook 中文版☆68Updated 5 months ago
- Learning Machine Learning, The Chinese Taoist Way☆433Updated 5 years ago
- 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。☆410Updated last month
- ☆317Updated last month
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆838Updated 3 weeks ago
- The repository has collected a batch of noteworthy MLSys bloggers (Algorithms/Systems)☆269Updated 7 months ago
- OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)☆226Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆669Updated 4 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆104Updated 3 months ago
- This repo is used for archiving my notes, codes and materials of cs learning.☆45Updated this week
- Hooked CUDA-related dynamic libraries by using automated code generation tools.☆165Updated last year
- A kubernetes plugin which enables dynamically add or remove GPU resources for a running Pod☆127Updated 3 years ago
- HAMi-core compiles libvgpu.so, which ensures hard limit on GPU in container☆199Updated last week
- A light llama-like llm inference framework based on the triton kernel.☆146Updated 2 weeks ago
- Device-plugin for volcano vgpu which support hard resource isolation☆101Updated last month
- ☆535Updated last year
- CUDA 算子手撕与面试指南☆541Updated 7 months ago
- ☆124Updated 6 months ago
- A pupil in the computer world.(Felix Fu)☆243Updated last year