#
Hugging Face Programming Tutorials & Engineering Articles
342 Hugging Face tutorials, guides, and engineering insights from NVIDIA, Google, ClickHouse, and more
Companies Using This
Hugging Face Articles & Tutorials
Filter:
Running a frontier-scale model locally means keeping all its weights in GPU memory; the largest models no longer fit on one machine. Two NVIDIA DGX Stations…
Fatima Fall
17 min read
Includes Code
--
Human motion offers roboticists a great starting point for teaching humanoid robots how to move. A human demonstration captures the coordination and timing…
John Malaska
8 min read
Includes Code
--
Autonomous vehicle (AV) developers need reasoning models that can operate within the compute and latency constraints of an onboard system.
Marco Pavone
12 min read
Includes Code
--
ClickHouse Managed Postgres is generally available, ClickHouse Observability enters public beta, ClickHouse Security launches in private preview, Langfuse introduces an open-source AI Gateway, and ClickHouse acquires Xata.
9 min read
Includes Code
--
Google AI Edge Gallery now supports on-device, offline Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) capabilities for building developer-friendly voice applications. Developers can leverage ML Kit for optimized Android performance, or use MediaPipe Tasks and LiteRT for cross-platform open-weight model integration. This local pipeline seamlessly pairs lightweight speech models with on-device small language models like Gemini Nano and Gemma 4 to enable real-time streaming transcription and low-latency synthesis.
Google AI Edge Team, Android ML Team
9 min read
--
Physical AI developers working with world models face two distinct challenges: adapting models to their sensors, tasks, and data, and getting those models into…
Elizabeth Goodman
9 min read
Includes Code
--
AI is expanding beyond the data center as developers build a new generation of agents to act at the edge: monitoring driver attention and cabin conditions…
Shara Tibken
5 min read
Includes Code
--
Building an autonomous agent requires a model, a harness, and domain-specific tools. To deploy an agent more securely, developers need a runtime that enforces…
Nicola Sessions
6 min read
--
As AI adoption expands globally, people across languages and cultures are using it in more aspects of their daily lives. General-purpose language models serve…
Shara Tibken
15 min read
Includes Code
--
Teaching a robot to navigate an obstacle course requires more than a walking policy. It must perceive its surroundings, maintain balance, and adjust its actions…
Gabriele Leone
10 min read
Includes Code
--
Protein design is a search problem. Choose amino acids for an eight-residue protein sequence and more than 25 billion combinations are possible.
Building an AI factory digital twin requires developers to bring site plans, equipment assets, and engineering requirements into a consistent model that teams…
Tanya Lenz
13 min read
--
Sidekick’s frontier model hands its most token-heavy work to open models that Shopify post-trains and serves itself. Here’s the loop we use to build them, and where NVIDIA’s models, software, and GPUs make each turn faster and cheaper.
Andrew McNamara
6 min read
--
Google AI Edge Model Explorer now supports custom compiler intermediate representations and open-source adapters like TOSA, VGF, and PTE for on-device machine learning. Developers can leverage hierarchical graph visualization, split-pane views, and per-node trace overlays to catch export regressions and verify hardware delegation. These tools enable engineering teams to transparently debug execution graphs and pinpoint cycle-level latency bottlenecks locally.
Eric Yang, Alan Ma
4 min read
Includes Code
--
TorchTPU integrates a native torch.device("tpu") backend directly into PyTorch, allowing developers to train large-scale models on Google Cloud TPUs without rewriting code in JAX. The TorchTitan TPU fork enhances this with production-grade scaling primitives like SimpleFSDP, Graph Trainer, and custom Pallas kernels that achieve high Model Flops Utilization (MFU) across dense and MoE architectures. Developers can leverage these battle-tested optimization playbooks, recipes, and the Hugging Face modeling backend to efficiently scale their own workloads on TPU infrastructure.
Aleksey Vlasenko, Rob Torres, Will Constable
22 min read
Includes Code
--
Meet the LiteRT Tensor API: giving developers native C++ control over the model graph to unify end-to-end ML computations on heterogeneous edge hardware.
Ping Yu, Quentin Khan, Chintan Parikh, Lu Wang
10 min read
Includes Code
--
Meta launches Muse Spark Open, a coding-optimized 816B mixture-of-experts (MoE) model with 42B active parameters and a 1M token context window.
Tanya Lenz
5 min read
--
Always-on agents are taking on longer, more complex enterprise workflows. A single request can involve reading a document, checking information across sources…
Michelle Horton
11 min read
--
EmbeddingGemma 2 is a compact, open-source multimodal embedding model that maps text, code, images, video, and audio into a unified 768-dimensional space. Developers can use the sentence-transformers library to selectively load modular modality encoders—ranging from 270M to 740M parameters—to optimize memory usage. Additionally, Matryoshka Representation Learning enables dynamic dimension truncation down to 128d, significantly reducing vector database storage requirements while maintaining high retrieval performance.
Maarten Grootendorst, Ian Ballantyne
7 min read
Includes Code
--
EmbeddingGemma 2 is a new 740M open-weight multimodal model that maps text, images, video, and audio into a unified vector space for privacy-first, on-device retrieval. Developers can easily integrate these capabilities cross-platform using MediaPipe Tasks or optimize fine-grained performance across CPU, GPU, and NPU accelerators with LiteRT. The model enables ultra-low-latency local solutions like search-as-you-type media retrieval, keyframe video moments finding, and zero-shot intent routing.
Google AI Edge Team, Android ML Team
11 min read
Includes Code
--
Adding AI models to local applications requires a portable model format, a reliable runtime, and acceleration that works across target systems.
Luca Spindler
3 min read
Includes Code
--
Automatic speech recognition must handle how people actually speak, not only the languages and styles that dominate pretraining data.
Elizabeth Goodman
13 min read
Includes Code
--
Parallel work, model-family isolation, reversible changes, and GPU-backed validation shaped an open source project designed around coding agents NVIDIA TensorRT…
Tanya Lenz
10 min read
Includes Code
--
As language models grow, scaling dense architectures becomes increasingly expensive. In a dense transformer, every token passes through every layer…
Michelle Horton
6 min read
Includes Code
--
Radiology AI has made remarkable strides in detecting abnormalities across chest X-rays, pathology slides, and 2D scans. Yet one of the most clinically rich and…
Tanya Lenz
11 min read
Includes Code
--
An AI coding agent’s patch can pass tests yet fail when the server loads a real model and handles requests. Evaluating changes to inference-serving software…
Elizabeth Goodman
7 min read
Includes Code
--
When you ship an AI agent, the key question is whether it can execute a chain of work across dozens of sequential tool calls against a live environment…
Elizabeth Goodman
10 min read
Includes Code
--
How can a 30B-parameter model activate only 3B parameters per token, and still use the capacity of the larger model? Nemotron 3.5…
Elizabeth Goodman
8 min read
--
NVIDIA has one of the largest and most complex supply chains in the world, and its performance is measured from wafer-out to first token. The interval is in two…
Elizabeth Goodman
11 min read
--
The surge in AI adoption is transforming everything from chatbots to content generation. Still, a common pain point remains: How can organizations confidently…
Elizabeth Goodman
12 min read
Includes Code
--
A perception stack is shaped by the vehicle that carries it. Move the same software to a new carline—for example, from an SUV to a sedan or another vehicle…
Michelle Horton
14 min read
Includes Code
--
Deploy an Open Model from Checkpoint to Inference in Two Commands with NVIDIA TensorRT Model Connect
Open AI models are evolving faster than ever, but bringing them into native applications can still require model-specific conversion, preprocessing…
Tanya Lenz
6 min read
Includes Code
--
Navigation enables a robot to turn perception and motion into purposeful autonomy. Unlike locomotion, which produces stable movement, navigation must be used to…
Tanya Lenz
15 min read
Includes Code
--
Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate.
Michelle Horton
3 min read
--
Robots need policies that can adapt to their sensors, environments, and tasks while running on onboard computing hardware. World models offer a foundation for…
Michelle Horton
10 min read
Includes Code
--
Teams customize their models to hit their targets for latency, speed, memory, and compute. With the open NVIDIA Nemotron family of models…
Tanya Lenz
18 min read
Includes Code
--
Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), its largest open-weight model, bringing near-frontier capabilities to the open ecosystem.
Michelle Horton
4 min read
--
Long-running AI agents spend most of their time on high-volume execution: tool calls, result validation, and subagent delegation. Using a frontier reasoning…
Tanya Lenz
8 min read
--
Learn how NVIDIA NeMo Switchyard routes AI agent workloads across models using tuning-free and tunable routers that balance model capability, cost, and latency.
Michelle Horton
11 min read
--
Deploying secure, real-time Edge AI on Raspberry Pi is now simplified using LiteRT and lightweight Gemma open models. LiteRT optimizes CPU and GPU performance, delivering fast token speeds for models like Gemma4, enabling real-time local reasoning for robotics. Developers can quickly convert, quantize, and run these models using the lightweight LiteRT CLI tool. Support for Hailo AI accelerators is also coming very soon.
Lu Wang, Terry Heo, Naushir Patuck, José María Casanova
9 min read
Includes Code
--
Meta returns to the open source ecosystem with the release of Muse Glimmer, a 30B open-weight dense model with a 120K+ context window built for local AI agentic…
Michelle Horton
4 min read
--
The 2026-07-28 Model Context Protocol (MCP) specification replaces legacy stateful constraints with a fully stateless core, enabling cloud-native horizontal scaling, serverless deployments, and standard round-robin load balancing. This architectural shift introduces standardized HTTP headers for efficient routing without deep packet inspection, caching controls, and Multi Round-Trip Requests (MRTR) to handle interactive and long-running tasks without blocking connections. Developers can immediately begin migrating their agentic applications to this highly scalable infrastructure using the newly available beta SDKs for Python, TypeScript, Go, and C#.
CachingGoogle CloudGoogle Cloud FunctionsHugging FaceJavaScriptJSONKubernetesPythonRedisServer-Sent EventsServerlessShellTypeScript
Kurtis Van Gent, Alan Blount
10 min read
Includes Code
--
A central challenge in robotics is building policies that generalize beyond the demonstrations they’re trained on. A policy that succeeds in a training scene…
Michelle Horton
7 min read
--
Autonomous vehicle (AV) development often relies on separate models for trajectory generation, high-level intent prediction, scene understanding…
Elizabeth Goodman
12 min read
Includes Code
--
ClickHouse is joining the Open Secure AI Alliance alongside NVIDIA and other industry leaders to help build open tools that keep AI agents secure.
5 min read
--
Unlike autonomous driving or industrial robotics, healthcare robotics can’t rely on internet-scale data collection or unlimited real-world experimentation.
Michelle Horton
11 min read
Includes Code
--
NVIDIA Ising Calibration is an open source vision language model (VLM) designed to interpret diagnostic outputs from quantum processors and determine how they…
Tanya Lenz
4 min read
--
Modern chip design is increasingly limited by engineering time. Register transfer level (RTL) development and verification require specialized hardware…
Elizabeth Goodman
8 min read
--