Using NVIDIA Management Library (NVML) in Rust
Intro to singe-nvml Rust crate.
Tin Rabzelj
Software engineer.
Latest posts
How to Debug a Deadlock
How to debug a deadlock in Rust?
Async Primitives for TypeScript
A collection of async primitives for TypeScript. Queue, Mutex, AsyncStream, delay, throttle, and more.
Trying to Build a Serverless Platform using Firecracker
Can I build my own AWS Lambda, though?
Building a Vector Database in Rust: LSM-VEC
Combining LSM-tree storage with HNSW-like routing to provide update-friendly disk-based vector search.
A Result Type for TypeScript
Did somebody ask for a monad?
Generating Sitemaps in TanStack Start
How can we generate a sitemap in a TanStack Start app?
Blockwise Parallel Transformer for Large Context Models | Paper Notes
Paper notes for Blockwise Parallel Transformer for Large Context Models.
Fast Inference from Transformers via Speculative Decoding | Paper Notes
Paper notes for Fast Inference from Transformers via Speculative Decoding.
Fast Transformer Decoding: One Write-Head is All You Need | Paper Notes
Paper notes for Fast Transformer Decoding: One Write-Head is All You Need.
GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints | Paper Notes
Paper notes for GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.
Ring Attention with Blockwise Transformers for Near-Infinite Context | Paper Notes
Paper notes for Ring Attention with Blockwise Transformers for Near-Infinite Context.
Effective Long-Context Scaling of Foundation Models | Paper Notes
Paper notes for Effective Long-Context Scaling of Foundation Models.
YaRN: Efficient Context Window Extension of Large Language Models | Paper Notes
Paper notes for YaRN: Efficient Context Window Extension of Large Language Models.
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention | Paper Notes
Paper notes for Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention.
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness | Paper Notes
Paper notes for FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness.
Longformer: The Long-Document Transformer | Paper Notes
Paper notes for Longformer: The Long-Document Transformer.
ReAct: Synergizing Reasoning and Acting in Language Models | Paper Notes
Paper notes for ReAct: Synergizing Reasoning and Acting in Language Models.
RoFormer: Enhanced Transformer with Rotary Position Embedding | Paper Notes
Paper notes for RoFormer: Enhanced Transformer with Rotary Position Embedding.
The Impact of Positional Encoding on Length Generalization in Transformers | Paper Notes
Paper notes for The Impact of Positional Encoding on Length Generalization in Transformers.
Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation | Paper Notes
Paper notes for Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation.
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models | Paper Notes
Paper notes for Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.
Tree of Thoughts: Deliberate Problem Solving with Large Language Models | Paper Notes
Paper notes for Tree of Thoughts: Deliberate Problem Solving with Large Language Models.
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer | Paper Notes
Paper notes for Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer | Paper Notes
Paper notes for Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer.
Language Models are Few-Shot Learners | Paper Notes
Paper notes for Language Models are Few-Shot Learners.
Language Models are Unsupervised Multitask Learners | Paper Notes
Paper notes for Language Models are Unsupervised Multitask Learners.
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding | Paper Notes
Paper notes for BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.
Improving Language Understanding by Generative Pre-Training | Paper Notes
Paper notes for Improving Language Understanding by Generative Pre-Training.
Attention Is All You Need | Paper Notes
Paper notes for Attention Is All You Need.
Neural Machine Translation by Jointly Learning to Align and Translate | Paper Notes
Paper notes for Neural Machine Translation by Jointly Learning to Align and Translate.
Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference | Paper Notes
Paper notes for Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference.
Sequence to Sequence Learning with Neural Networks | Paper Notes
Paper notes for Sequence to Sequence Learning with Neural Networks.
GloVe: Global Vectors for Word Representation | Paper Notes
Paper notes for GloVe: Global Vectors for Word Representation.
Efficient Estimation of Word Representations in Vector Space | Paper Notes
Paper notes for Efficient Estimation of Word Representations in Vector Space.
Pointers Are Not Just Integers - Provenance
A pointer is just the address of a memory location, right?
Building a Real-Time Bluesky Trending Hashtag System With Arroyo, NATS, and Rust
Let's talk about building a real-time trending hashtag system.
From a Monolith to Microservices
How to go from a monolith to microservices and should you?
How To Use Raylib in Rust With Your Own Bindings
Learn how to create custom Rust bindings for Raylib and how to approach C interoperability in general.
Introduction to Intelligent Agent Architectures
What are intelligent agents anyway?
Validate Next.js Server Actions with Zod
This is a simple utility I wrote to validate Next.js server actions with Zod.
Working With CUDA in Rust - Basic FFI
Let's work with CUDA in Rust without external crates.
PostgreSQL and process-per-connection
Processes being units of concurrency is silly, right?
Mojo Outperforms Rust?
Some thoughts about "Mojo outperforming Rust".
How I Use Declarative Macros in Rust
Showing my common use cases for declarative macros in Rust.
Running Next.js Standalone App With Sharp Inside Docker
Running Next.js standalone app with sharp inside Docker cannot be that hard, right?
Error Handling Pattern with React and Redux-Saga
This article describes an error handling pattern with React and Redux-Saga.
Generating Realistic Test Traffic Using Markov Chains
This article shows how to generate realistic traffic using Markov Chains.
Why Should Microservices Be Idempotent
This article gives an argument on why services in microservices architecture should always be idempotent.
Rate Limiting in Rust Using Redis
This article shows how to perform rate limiting in Rust using Redis.