AI Resources

AI resources provides a centralized hub for the latest and most relevant research papers on large language models (LLMs), Generative AI, machine learning (ML) systems, optimizations and compilers. These resources offer researchers, developers, and hackers easy access to the latest research. By distilling complex information into digestible summaries, AI resources help streamline the research process, enabling quicker implementation of new ideas and techniques into practical applications across the AI stack.

Browse by category

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

AI Resources

LLM Context Evaluations

High Performance Computing (HPC) Technical Primer

Ring Attention with Blockwise Transformers for Near-Infinite Context

Attention with Linear Biases Enables Input Length Extrapolation (ALiBi)

YaRN: Efficient Context Window Extension of Large Language Models

Gemini: A Family of Highly Capable Multimodal Models

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Efficient Memory Management for LLM Serving with PagedAttention

MLIR: A Compiler Infrastructure for the End of Moore’s Law

RoBERTa: A Robustly Optimized BERT Pretraining Approach

Large Language Model Technical Primer

Contrastive Language-Image Pre-training (CLIP)

ML Compiler Technical Primer

AI & Memory Wall

Quantization Technical Primer

Mixtral of Experts

Llama 2

Byte Pair Encoding (BPE)

FlashAttention

FlashAttention-2

Mistral-7B

Phi-3-mini

Gemma: Open Models Based on Gemini Research and Technology

Grouped Query Attention

Rotary Position Embedding (RoPE)