V Programming Tutorials & Engineering Articles

The article discusses NVIDIA TensorRT LLM AutoDeploy, a beta feature that automates the inference optimization process for large language models (LLMs).

This article introduces Dynamic Context Parallelism (Dynamic-CP), a scheduling approach in NVIDIA Megatron Core designed to optimize training for variable-length sequences in large-scale models.

PinLanding is a multimodal AI pipeline developed by Pinterest to generate shopping collections from billions of products.

The article discusses the advancements in AI technologies and infrastructure that shaped the year 2025, focusing on NVIDIA's innovations in AI factories, physical AI, and model optimization.

The article discusses the Skip Softmax technique, a method for accelerating long-context inference in large language models (LLMs) using NVIDIA TensorRT-LLM.

The article highlights Alexey's favorite features introduced in ClickHouse throughout 2025, including lightweight updates, data lake support, and advancements in text and vector indexing.

The article discusses NVFP4 KV cache quantization, a new key-value format that significantly enhances inference performance on NVIDIA Blackwell GPUs.

The article discusses neural shading as a transformative approach to real-time rendering, integrating trainable models into graphics pipelines to enhance visual fidelity and performance.

The NVIDIA Blackwell architecture has achieved the fastest training times across all MLPerf Training v5. 1 benchmarks, showcasing significant advancements in AI training performance.

This article discusses how to enhance log compression through log clustering techniques in ClickHouse, focusing on transforming unstructured logs into structured data for efficient storage.

The article discusses the introduction of QBit, a new column type in ClickHouse that allows for flexible precision in vector search queries.

The article discusses the enhancements in cuBLAS with the introduction of floating-point emulation for Tensor Core performance, particularly focusing on double-precision (FP64) matrix multiplicatio...

This article discusses the optimization of vision AI workloads using NVIDIA's CUDA-accelerated implementation of SMPTE VC-6, a codec designed for efficient interaction with modern compute architect...

ClickHouse version 25. 8 introduces 45 new features, 47 performance optimizations, and 119 bug fixes, enhancing its capabilities as a high-performance analytical database.

The article discusses the optimization of large language models (LLMs) through post-training quantization (PTQ), emphasizing its benefits in enhancing inference performance while maintaining accura...

The article discusses CUTLASS, a library developed by NVIDIA for handling multidimensional data through tensors and spatial microkernels. It highlights the advancements in CUTLASS 3.

The article discusses the process of porting CPU applications to NVIDIA GPUs to enhance performance, particularly in the context of Électricité de France's (EDF) fluid dynamics simulations using th...

The article discusses the advancements in large language models (LLMs) focusing on the importance of extended context lengths for processing and generating text.

The article discusses the modernization of Pinterest's home feed pre-ranking stage, focusing on the introduction of a sophisticated pre-ranking layer known as Lightweight Scoring.

NVIDIA has set a new world record for large language model inference speed, achieving over 1,000 tokens per second per user with the 400-billion-parameter Llama 4 Maverick model on a single NVIDIA ...

NVIDIA is pioneering the shift to 800 VDC architecture to meet the growing power demands of AI factories, moving beyond traditional 54 V systems.

NVIDIA has announced the general availability of Secure AI, focusing on protecting data and code during AI training and inference, particularly for large language models (LLMs).

The article discusses the Marco framework, a configurable graph-based task-solving and multi-AI agent system designed to streamline chip design processes.

This article discusses how to build a movie recommendation system using NetworkX, Jaccard Similarity, and NVIDIA cuGraph to enhance performance.

The article discusses the implementation of an automated GenAI-driven search quality evaluation system for LinkedIn's typeahead suggestions.

Researchers from Weill Cornell Medicine have developed the Blastocyst Evaluation Learning Algorithm (BELA), an AI-powered model that enhances embryo selection in in vitro fertilization (IVF) by eva...

The article discusses the development of a 172 billion parameter large language model (LLM) with strong Japanese capabilities using NVIDIA Megatron-LM.

The article discusses the integration of the AWS Energy HPC Orchestrator with NVIDIA Energy Samples to enhance high-performance computing (HPC) in the energy sector.

The article discusses the integration of NVIDIA's NVENC technology with V-Nova's MPEG-5 Part 2 Low-Complexity Enhancement Video Coding (LCEVC) standard to create customizable GPU-accelerated video ...

The article discusses NVIDIA's advancements in audio generative AI with the introduction of BigVGAN v2, a universal neural vocoder that synthesizes audio waveforms with state-of-the-art quality and...

NVIDIA has fully transitioned to open-source GPU kernel modules with the upcoming R560 driver release, enhancing support for various GPU architectures while providing substantial new capabilities.

The article discusses how LinkedIn is utilizing data to enhance skills-based hiring through a feature called Skills Match.

The article discusses the integration of advanced AI and Retrieval-Augmented Generation (RAG) techniques in high-performance computing (HPC) code development.

This article discusses the advancements in graph analytics through a next-generation architecture utilizing NVIDIA cuGraph acceleration.

NVIDIA has announced the general availability of its Confidential Computing solution on NVIDIA H100 Tensor Core GPUs, which provides enhanced security for data in use, particularly for AI applicati...

This article explores how ClickHouse can be utilized as a feature store to train machine learning models, specifically focusing on the integration with Featureform.

The article discusses the application of Mixture of Experts (MoE) in large language model (LLM) architectures, highlighting its benefits in terms of model capacity, cost efficiency, and latency red...

The article discusses the importance of using shader debugging information with NVIDIA Nsight Graphics for optimizing shader performance in ray tracing applications.

This article discusses the implementation of Video Multi-Method Assessment Fusion (VMAF) using NVIDIA GPUs and CUDA, highlighting the performance improvements and advantages of VMAF-CUDA over tradi...

This article discusses the emulation of the attention mechanism in transformer models using a fully convolutional network, specifically targeting improvements in computer vision tasks.

The article discusses the evolution of ads conversion optimization models at Pinterest, highlighting the transition from Gradient Boosted Decision Trees (GBDT) to advanced Deep Neural Networks (DNN...

ClickHouse Release 23. 11 introduces a wealth of new features, performance optimizations, and bug fixes, enhancing its capabilities for data processing and analytics.

This article discusses inference optimization techniques for large language models (LLMs), highlighting the challenges and solutions associated with memory and compute efficiency.

The article discusses the intricacies of training Large Language Models (LLMs) using transformer networks, focusing on model architectures, attention mechanisms, and embedding techniques.

NVIDIA's Differentiable Slang is a new shading language designed to unify real-time, inverse, and differentiable rendering, enabling seamless integration of machine learning with graphics programmi...

This article explores how to analyze Hugging Face datasets using ClickHouse, specifically through the clickhouse-local tool.

The article discusses the design of deep neural networks (DNNs) that can process the weights of other DNNs, focusing on architectures that leverage the symmetries of weight spaces.

NVIDIA OptiX 8 is a powerful ray tracing framework that leverages GPU acceleration to create photorealistic visuals efficiently.

The article discusses the new features introduced in NVIDIA's Video Codec SDK 12. 1, focusing on GPU-accelerated video processing through NVENC and NVDEC.

Microsoft and TempoQuest have collaborated to enhance wind energy forecasting using AceCAST, a GPU-accelerated version of the Weather Research and Forecasting (WRF) model.