Resources
Primary papers, production runtimes, and evaluation benchmarks referenced throughout the tutorials and architecture deep dives on largo.dev.
AI Systems Engineering Lab: GPU VRAM, Hybrid Retrieval & Agent Memory
Explore all three production AI workbenches in one place: size GPU VRAM and MHA/GQA/Hybrid/MLA KV caches from 2K to 128K context, model two-stage BM25 + dense RRF and cross-encoder reranking latency SLOs, and compare quadratic transcript growth against active-slot agent memory consolidation.
Foundational & Frontier Papers
Reciprocal Rank Fusion Outperforms Condorcet and Individual Rank Learning Methods
Cormack, Clarke & Buettcher, 2009
Introduced rank-based 1 / (k + r) score fusion across lexical and semantic retrieval lists without brittle score-distribution calibration.
Attention Is All You Need
Vaswani et al., 2017
Introduced scaled dot-product and multi-head self-attention, replacing recurrent bottlenecks with parallelizable sequence modeling.
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reimers & Gurevych, 2019
Reduced pairwise semantic similarity search from hours of cross-encoder inference to milliseconds with bi-encoder vector spaces.
Dense Passage Retrieval for Open-Domain Question Answering
Karpukhin et al., 2020
Demonstrated how dual-encoder training with in-batch and hard BM25 negatives outperforms lexical retrieval alone on open-domain QA.
ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction
Khattab & Zaharia, 2020
Preserves token-level MaxSim matching while precomputing document representations offline, bridging bi-encoder speed and cross-encoder accuracy.
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis et al., 2020
Coupled non-parametric dense retrieval indices with sequence-to-sequence generation so grounded facts can update without retraining weights.
LoRA: Low-Rank Adaptation of Large Language Models
Hu et al., 2021
Freezes pre-trained model weights and injects trainable rank-decomposition matrices into linear layers, enabling compact multi-tenant serving adapters.
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
Dao, 2023
IO-aware exact attention tiling across GPU SRAM and HBM that makes long-context training and serving practical at high FLOP utilization.
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Gu & Dao, 2023
Input-dependent state space selection with hardware-aware parallel scan, achieving linear O(N) scaling on long sequences and telemetry streams.
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
DeepSeek-AI, 2025
Showed how Group Relative Policy Optimization (GRPO) against verifiable rewards elicits multi-step reasoning and self-verification without dense process supervision.
mHC: Manifold-Constrained Hyper-Connections (arXiv:2512.24880)
DeepSeek-AI, 2025
Projects multi-stream residual mixing matrices onto the Birkhoff polytope via Sinkhorn-Knopp iterations, bounding activation gain across deep MoE training.
Tools & Runtime Stack
PyTorch & torch.compile
RuntimeCore tensor runtime and TorchInductor graph compiler for training, quantization, and sub-millisecond kernel fusion.
vLLM
ServingHigh-throughput LLM serving engine with PagedAttention, continuous batching, speculative decoding, and prefix caching.
Pydantic
ContractsSchema-first validation boundary for typed tool contracts, structured model outputs, and runtime configuration.
sentence-transformers
EmbeddingsReference library for training, fine-tuning, and benchmarking bi-encoder embeddings and cross-encoder rerankers.
FAISS
Vector SearchC++ and GPU library for HNSW, IVF, and product-quantized vector indexing when testing recall-latency trade-offs.
Hugging Face Transformers
ModelsModel definitions, tokenizers, and safetensors weight loading across open-weight language, vision, and multimodal architectures.
Hugging Face PEFT & TRL
Fine-TuningParameter-efficient LoRA/QLoRA adapter injection and supervised post-training pipelines for open-weight Transformer and MoE backbones.
ONNX Runtime
InferenceCross-platform inference execution provider for CPU/GPU graph optimization, INT8 quantization, and portable deployment.
Model Context Protocol (MCP)
AgentsOpen JSON-RPC specification standardizing how agent runtimes discover and invoke typed tools, resources, and prompts.
Google Agent Development Kit (ADK)
AgentsCode-first Python and Java framework for typed agent workflows, session state scopes, and managed Vertex AI Memory Bank integration.
LangGraph
AgentsExplicit state-machine runtime for cyclic and parallel agent graphs, checkpointed execution, and conditional edge routing.
Evaluation & Retrieval Benchmarks
SWE-bench Verified
500 tasksHuman-validated real GitHub issues paired with unit-test patches for measuring end-to-end software engineering agents.
BEIR
18 datasetsZero-shot retrieval suite across biomedical, financial, scientific, and fact-checking domains to expose overfitting.
MS MARCO
8.8M passagesWeb passage ranking corpus built from anonymized search queries; standard baseline for dense retrieval and reranking.
Natural Questions
307K examplesSearch queries paired with full Wikipedia articles and annotated long/short answers for grounded QA evaluation.
HotpotQA
113K examplesMulti-hop question answering benchmark with sentence-level supporting facts to test iterative retrieval and reasoning.
MTEB
58 datasetsMassive Text Embedding Benchmark spanning retrieval, clustering, pair classification, reranking, and STS tasks.