636
76
Learn how to deploy Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter open-weight model, on Amazon SageMaker HyperPod with vLLM. This walkthrough covers cluster provisioning, NVFP4 quantization, and an OpenAI-compatible endpoint with built-in reasoning, tool calling, and native MTP speculative decoding.
At Wednesday's iPhone Duo launch event, Apple announced a handful of new Siri AI Audio Intelligence features, including Siri Recap, Live Rewind, Sound Recognition, and…
A recap of August 2026 launches for AI builders across Amazon Bedrock, Amazon Bedrock AgentCore, and Strands: million-token context for OpenAI models, cross-Region inference, agents that run for up to 14 days on dedicated compute, expanded AWS GovCloud availability, and Strands Robots for physical deployment.
Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence into robot control remains challenging. We present Show-Harness, an Embodied Harness that enables VLMs to "play" robots through a compact semantic interface linking intent to action. Show-Harness exposes discrete semantic action units that VLMs can naturally reason over, while embodiment-specific interpreters deterministically ground them into local robot actions, keeping the VLM directly responsible for fine-grained physical decisions. Through the same interface, Show-Harness demonstrates the feasibility of (1) directly unlocking closed-source frontier VLMs for zero-shot robot control, and (2) adapting small-scale open-source VLMs for low-cost deployment with just a few GPU-hours of fine-tuning. We further develop GUMI (GUI Manipulation Interface), which extends the same semantic action space to GUI-based demonstration collection, allowing humans and agents to "play" robots across embodiments without specialized teleoperation hardware. Extensive experiments show that Show-Harness-equipped VLM agents generalize robustly across tasks, embodiments, and environments, outperforming representative agentic and VLA paradigms. These results suggest that the right interface can unlock substantial embodied capability from foundation VLMs, without requiring additional model capacity or costly embodiment-specific pretraining.
At the IBC conference, running Sept. 11-14 in Amsterdam, the creative, technology and business communities are coming together to turn ideas into action and discuss innovations across the media and entertainment industries. More than 44,000 attendees from 170+ countries are gathering to explore 1,300+ exhibitions in 14+ halls and outdoor spaces, with over 600 speakers […]
TorchServe is no longer maintained, leaving teams to own the entire GPU inference stack. The AWS Ray Serve Deep Learning Container is a supported, pre-tested container with the framework, GPU drivers, and serving layer already assembled. This post walks through deploying a vision-language model on Amazon EKS using the Ray Serve DLC on a single GPU node.
GPT-6 Astra from OpenAI is now generally available on Amazon Bedrock. It brings deeper reasoning and sharper judgment to your most demanding tasks, running on the Amazon Bedrock inference engine built for high performance, security, and scale.
Pathway's Baby Dragon Hatchling (BDH) is a brain-inspired, post-transformer architecture that reasons in latent space instead of emitting chain-of-thought tokens. See how Pathway develops and scales BDH on Amazon SageMaker HyperPod, and how BDH-CQ set a new cost-efficiency mark on the ARC-AGI-1 benchmark.
Pathway's Baby Dragon Hatchling (BDH) is a brain-inspired, post-transformer architecture that reasons in latent space instead of emitting chain-of-thought tokens. See how Pathway develops and scales BDH on Amazon SageMaker HyperPod, and how BDH-CQ set a new cost-efficiency mark on the ARC-AGI-1 benchmark.
While many video-game environments (VGEs) have played crucial roles in advancing reinforcement learning (RL), developing novel VGEs or modifying existing ones to support new features, has been a laborious process requiring extensive hand-coding. Here we present PlayTrain, an RL framework that combines the abilities of large language models (LLMs) to robustly generate JavaScript (JS) games from a minimal human prompt, and an efficient pipeline that can run any JS game in a standard 'gym' environment. Not only are recent LLMs particularly good at writing JS code, but the JS format also allows users to easily play generated VGEs, while PlayTrain enables us to train RL agents on the exact same games. We demonstrate multiple use cases of PlayTrain, including cloning well-known Atari and ProcGen games in simple JS, where PlayTrain trains pixel-based agents end-to-end at over 1M agent-decisions per second on a single GPU node; and creating modified versions thereof (e.g., that support novel test sets, procedural generation logics, or game dynamics). Through PlayTrain, we reimagine RL VGE development: all we need is a single JS file, generated and modified through an LLM. We discuss promising future RL research directions that PlayTrain unlocks.
Benchmark two 30B Mixture-of-Experts models, Qwen3-Coder-30B and NVIDIA Nemotron-3-Nano-30B, across G5, G6, G6e, and G7 GPU instances on Amazon SageMaker AI. Compare throughput, latency, and cost-per-token, and see how G7's NVIDIA Blackwell GPUs deliver measurable price-performance gains for real-time LLM inference.
In September 2026, NVIDIA announced it is leaning into native GPU programming in Rust. CUDA C++ and CUDA Python are mature, enterprise-grade toolchains, and...
Machine-learning performance modeling is a uniquely hostile terrain for long-lived software: the assumptions baked into today's abstractions are invalidated by tomorrow's models and systems, forcing perpetual refactoring of performance-modeling frameworks. Meanwhile, AI coding agents have become fast and capable enough that regenerating an entire library is cheaper than paying down the tech debt of incrementally patching it. We describe SMART, a rigorous symbolic performance-modeling library for ML systems whose main branch contains almost no code: the repository is a DAG of self-contained natural-language design docs, coding sub-agents regenerate the implementation from only the docs on new version updates, and every human change is a natural-language edit to a doc--self-documenting by construction. Two ingredients make regeneration reliable: (i) a design-doc style built around step-by-step worked examples that act as in-context demonstrations for the generating agents, and (ii) a minimal, recursively defined operator IR with symbolic (SymPy) cost expressions, a fast analytical roll-up mode for large sweeps, and a slow modulo-scheduling mode for fine-grained schedule studies. Regenerated implementations reproduce hand-audited reference models--including DeepSeek-V3 serving on a TPU pod slice--to round-off precision, suggesting that design docs--not code--can be the durable artifact for ML-systems co-design tools.
Trade-up recommendation identifies higher-quality alternatives that preserve a customer's purchase intent while offering upgraded benefits. Large language models (LLMs) can reason about such distinctions, but applying them directly to hundreds of millions of product pairs is operationally impractical. We introduce a two-level framework that distills LLM reasoning into an efficient non-generative student and adapts its decision boundary to product-type-specific trade-up criteria. At Level 1, a retrieval-augmented few-shot LLM teacher generates structured relation labels and natural-language rationales. These rationales supervise a compact embedding-pair classifier through alignment and contrastive objectives; at inference, the student uses only two precomputed 768-dimensional product embeddings, with no LLM calls or text generation. On a fixed human-annotated benchmark of 8,352 pairs, a 15.5M-parameter four-class reasoning-distilled student achieves AUC 0.924 (95% CI [0.918, 0.929]), compared with 0.912 for the four-class label-only student. At Level 2, product-type test-time training (PT-TTT) uses few-shot demonstrations to optimize lightweight category-specific adapters over the frozen student. PT-TTT improves AUC from 0.924 to 0.941 and average precision from 0.920 to 0.940. On a 100K-pair proxy catalog, the distilled student on a single eight-GPU machine is approximately 5,000x faster and 10,000x lower in estimated cost than direct LLM inference.
Running reasoning and agentic AI at the edge has been harder than it needs to be. Until recently, models capable of multi-step reasoning were too large to run...
Building a Physical AI system takes a continuous pipeline, not a single training job. This post shows how to run that model factory (synthetic data generation, post-training, and closed-loop evaluation with NVIDIA Cosmos 3) on a persistent, resilient Amazon SageMaker HyperPod cluster on Amazon EKS, with GPU goodput as the metric that matters.
HyperPod InstantStart is an open source control plane that composes Amazon EKS orchestration with the managed capabilities of Amazon SageMaker HyperPod. It drives the same guarded operations through both a web interface and an AI agent, turning cluster bootstrap, capacity, training, inference, and storage into dependable, agent-driven infrastructure.
