The Role of MPI in Modern AI - Rusty Lusk's Legacy
Explore MPI's crucial role in modern AI and its impact on parallel computing, honoring Rusty Lusk's contributions to the field.
From Two Strong Oxen to Billions of Fleas - The Evolution of Massively Parallel Distributed Supercomputers
Explore massively parallel distributed supercomputers, focusing on distributed-memory parallelism and RDMA through MPI. Gain insights into current designs and future challenges in high-performance computing.
HammingMesh: A Network Topology for Large-Scale Deep Learning
Explore a novel network topology for large-scale deep learning systems, enhancing data movement efficiency and job scheduling flexibility for future AI training infrastructure.
AI-Driven Performance Metaprogramming - Embedding Spaces for Program Analysis and Optimization
Explore AI-driven performance metaprogramming using embedding spaces for programs. Learn to assess, analyze, and improve program performance through advanced AI methods.
HPC Carpentry: Bridging the Gap in High-Performance Computing Education
Learn essential skills for using high-performance computing resources effectively, bridging the gap for novice users and researchers in domains with newly available HPC access.
My Plan B: Exploring Alternative Strategies in Computer Science Research
Explore innovative approaches to software testing and verification with Professor Alastair Donaldson in his Imperial Inaugural lecture.
LLMs Anywhere - Browser Deployment with Wasm and WebGPU
Explore deploying ML models in browsers using Wasm and WebGPU. Learn to optimize performance, reduce cloud dependency, and enhance accessibility for efficient browser-based machine learning.
A Cloud-Native Parallel Data Processing Application in Julia
Explore cloud-native parallel data processing in Julia, covering design, debugging, and profiling techniques for high-performance applications. Learn AWS integration, containerization, and performance optimization strategies.
No More Runtime Setup - Bundling, Distributing, Deploying, and Scaling LLMs Seamlessly with Ollama Operator
Discover Ollama Operator: simplify LLM deployment, bundling, and scaling across environments. Eliminate runtime complexities and dependency issues for seamless large language model management in Kubernetes.
Write Once Run Anywhere for GPUs - Portable AI Workloads with Rust and WebAssembly
探讨LlamaEdge如何利用Rust和WebAssembly实现跨平台LLM应用开发,从基础推理到复杂RAG系统,展示其在云端和边缘设备上的灵活部署能力。
LLMs Anywhere - Browser Deployment with Wasm and WebGPU
Explore deploying ML models in browsers using Wasm and WebGPU, reducing cloud dependency and enabling offline access. Learn practical examples for efficient cross-platform execution and optimized computation.
Leveraging Wasm for Portable AI Inference Across GPUs, CPUs, OS and Cloud-Native Environments
Explore WebAssembly's advantages for AI inference in cloud-native ecosystems, enabling uniform performance across hardware, operating systems, and cloud environments while enhancing deployment and scalability.
Unlocking Heterogeneous AI Infrastructure K8s Cluster - Leveraging the Power of HAMi
探索HAMi项目如何优化异构AI设备在K8s集群中的管理,提高资源利用率,支持灵活调度策略,并解决实际生产环境中的挑战。
Unlocking the Parallel Universe: Subinterpreters and Free-Threading in Python 3.13
Explore Python 3.13's subinterpreters and free-threading for enhanced parallel execution. Learn implementation, limitations, and real-world applications in web server architecture.
Self-Hosted AI Image Generation with InvokeAI
Explore self-hosted AI image generation with InvokeAI. Learn to create and edit stunning visuals, generate set pieces, and integrate them into your projects. Includes hardware recommendations and practical demonstrations.
Unlocking the Parallel Universe: Subinterpreters and Free-Threading in Python 3.13
Explore Python 3.13's subinterpreters and free-threading for enhanced parallel execution. Learn implementation, limitations, and real-world applications in web server architecture.
Java Parsing Optimization: Processing 1 Billion Rows of Weather Data
Explore Java optimization techniques to parse 1 billion rows of weather data, covering parallelism, memory-mapped files, SWAR, bit twiddling, and Graal native compilation for impressive performance gains.
How to Build a Detectron2 Model with Roboflow and Paperspace Gradient
Learn to build a Detectron2 model using Roboflow for image preprocessing and Paperspace Gradient for GPU-backed training. Covers dataset access, image augmentation, and model development.
Building Your Own ChatGPT-style LLM AI Infrastructure with Kubernetes
Explore building AI infrastructure with Kubernetes, covering open-source LLMs, data engineering, and cost optimization. Gain insights on deployment, scalability, and choosing the right tools for AI-enabled applications.
std::simd - Expressing Inherent Parallelism Efficiently Via Data-parallel Types
Explore efficient data-parallelism using std::simd in C++26, learning to optimize compute-intensive workloads and design data structures for high-throughput execution.
Parallelism Safety-Critical Guidelines for C++
Explore parallelism safety guidelines for C++, covering challenges in multicore architectures and potential issues with newer features. Gain insights into future rules for safety-critical software development.