List of things I want to pick up at some time:

• <Insert here>
• Sparse AutoEncoder Explainability (https://adamkarvonen.github.io/machine_learning/2024/06/11/sae-intuitions.html)
• The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs >> MUST READ!
• 30 Papers (ilya)
• Top papers in LLMs + Top ViT papers
• https://x.com/youraimarketer/status/1778992208697258152 >> Cited By Karpathy as good
• https://github.com/karpathy/LLM101n → We can use this structure
• https://www.youtube.com/@umarjamilai
• https://huggingface.co/docs/transformers/main/en/quantization/overview

ray-project/llm-numbers: Numbers every LLM developer should know

Achieve 23x LLM Inference Throughput & Reduce p50 Latency

LLM Inference Optimizations — Continuous Batching (Dynamic Batching) and Selective Batching, Orca | by Don Moon | Byte-Sized AI | Medium

Generation with LLMs

serodriguez68/designing-ml-systems-summary: A detailed summary of "Designing Machine Learning Systems" by Chip Huyen. This book gives you and end-to-end view of all the steps required to build AND OPERATE ML products in production. It is a must-read for ML practitioners and Software Engineers Transitioning into ML.

LLM Inference Optimizations - Chunked Prefills and Decode Maximal Batching | by Don Moon | Byte-Sized AI

LLM Inference Series: 2. The two-phase process behind LLMs’ responses | by Pierre Lienhart | Medium

Large Scale Transformer model training with Tensor Parallel (TP) — PyTorch Tutorials 2.5.0+cu124 documentation

LLM Inference Series: 4. KV caching, a deeper look | by Pierre Lienhart | Medium