---

Link Dump

Interesting links I find on the internet. Mostly ml, computer system, low-level progamming and history.

Quest of This Week

Apr 12 - Apr 19 2025

• Efficient Memory Management for Large Language Model Serving with PagedAttention
• Speeding up the GPT - KV cache
• Transformer Inference Arithmetic
• EFFICIENTLY SCALING TRANSFORMER INFERENCE
• Large Transformer Model Inference Optimization
• How to deploy your deep learning side project on a budget
• Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better
• SparseDNN: Fast Sparse Deep Learning Inference on CPUs
• LoRA: Low-Rank Adaptation of Large Language Models
• A Visual Guide to Mixture of Experts (MoE)

Recent

Apr 01 - Apr 10 2025

• → Mastering LLM Techniques: Inference Optimization
• → A Survey on Efficient Inference for Large Language Models
• → LLM Inference Performance Engineering: Best Practices
• → Speculative Decoding: When Two LLMs are Faster than One
• → Quantization vs Pruning vs Distillation: Optimizing NNs for Inference
• → A Visual Guide to Quantization

Archive

March 01 - March 10 2025

• → The Key Equation Behind Probability
• → The KL Divergence : Data Science Basics
• → PyTorch internals