preacher-1 / MLA_tutorialLinks
from MHA, MQA, GQA to MLA by 苏剑林, with code
☆28Updated 6 months ago
Alternatives and similar repositories for MLA_tutorial
Users that are interested in MLA_tutorial are comparing it to the libraries listed below
Sorting:
- ☆102Updated 11 months ago
- pytorch distribute tutorials☆147Updated 2 months ago
- LLM101n: Let's build a Storyteller 中文版☆132Updated last year
- 从零构建MoE大模型:从预训练到DPO的完整实践☆52Updated this week
- 大模型/LLM推理和部署理论与实践☆321Updated last month
- LLM Tokenizer with BPE algorithm☆34Updated last year
- Inference code for LLaMA models☆122Updated 2 years ago
- an implementation of transformer, bert, gpt, and diffusion models for learning purposes☆156Updated 10 months ago
- DeepSpeed教程 & 示例注释 & 学习笔记 (大模型高效训练)☆176Updated last year
- Pipeline-Parallel Lecture: Simplest Dualpipe Implementation.☆27Updated 2 months ago
- 欢迎来到 "LLM-travel" 仓库!探索大语言模型(LLM)的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。☆338Updated last year
- WWW2025 Multimodal Intent Recognition for Dialogue Systems Challenge☆125Updated 9 months ago
- llm & rl☆198Updated last week
- 一些 LLM 方面的从零复现笔记☆217Updated 4 months ago
- ☆98Updated last year
- LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.☆815Updated last week
- 青稞Talk☆135Updated this week
- ☆85Updated 6 months ago
- simplest online-softmax notebook for explain Flash Attention☆13Updated 8 months ago
- LLM大模型(重点)以及搜广推等 AI 算法中手写的面试题,(非 LeetCode),比如 Self-Attention, AUC等,一般比 LeetCode 更考察一个人的综合能力,又更贴近业务和基础知识一点☆349Updated 8 months ago
- 主要记录大语言大模型(LLMs) 算法(应用)工程师多模态相关知识☆230Updated last year
- 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☆39Updated 3 weeks ago
- 训练一个对中文支持更好的LLaVA模型,并开源训练代码和数据。☆68Updated 11 months ago
- ☆113Updated 9 months ago
- Train a 1B LLM with 1T tokens from scratch by personal☆722Updated 4 months ago
- UltraScale Playbook 中文版☆71Updated 5 months ago
- A light llama-like llm inference framework based on the triton kernel.☆148Updated 3 weeks ago
- ☆369Updated 6 months ago
- 看图学大模型☆317Updated last year
- 最少使用 3090 即可训练自己的比特大脑(miniLLM)🧠(进行中). Train your own BitBrain(A mini LLM) with just an RTX 3090 minimum.☆33Updated 2 months ago