🚀 LLM Inference All-in-One 🌟

Your ultimate guide to resources, papers, and blogs on Large Language Model (LLM) inference techniques! 📚✨

---

🏆 Awesome Lists

Overview

• 🔗 Awesome-LLM-Inference
  A curated collection of papers and codes on LLM inference, including topics like FlashAttention, PagedAttention, and Parallelism.

• 🔗 Awesome LLM Systems Papers
  A curated list of Large Language Model systems related academic papers, articles, tutorials, slides and projects.

---

🌀 Speculative Decoding

• 🔗 Awesome-Speculative-Decoding
  Explore advanced methods for accelerating LLM decoding with speculative techniques. 🚀

• 🔗 COLING 2025 Tutorial: Speculative Decoding for Efficient LLM Inference
  Full slide deck, Recording, B站链接

---

📏 Long-Context Modeling

🔗 Large Language Model Based Long Context Modeling Papers and Blogs
Dive deep into papers and blogs on extending LLM context length, efficient transformers, and retrieval-augmented generation (RAG). 🧠✨

---

🧩 Mixture of Experts (MoE)

🔗 Awesome MoE LLM Inference System and Algorithm
A comprehensive list of resources for optimizing MoE-based LLM inference. Perfect for tackling sparse expert models! 🌟

---

🗂️ KV Cache Management

Efficient management of KV Caches for LLM acceleration! ⚡

• 🔗 Awesome-KV-Cache-Management
  Explore token-level, model-level, and system-level optimizations for KV Cache.
• 🔗 Awesome-KV-Cache-Compression
  Must-read papers on KV Cache compression for memory-efficient LLM inference.

---

📝 Resources

Explore insightful blogs and courses on cutting-edge LLM inference techniques! 🌐

Courses

🔗 入门必备 - Andrej Karpathy：从零开始构建 GPT 系列

🔗 MIT 6.5940 TinyML 和高效的深度学习计算

🔗 UCSD CSE 234: Data Systems for Machine Learning

🔗 CMU Large Language Model System Course

Blogs

🔗 Learning notes for ML System

🔗 A batch of noteworthy MLSys bloggers

Stay tuned for more updates! 🎉