Results for “inference”

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

Detect anomalies in time-series data using the Azure AI Anomaly Detector SDK for Java, with support for univariate and multivariate analysis, model training, and inference.

Trains, evaluates, exports, quantizes, and runs inference for a Grounding DINO model that detects objects described by text prompts without a fixed class vocabulary.

Fine-tune, evaluate, run inference, and export Cosmos-Embed1 video-text embedding models for tasks like text-to-video retrieval and semantic deduplication.

Run ML workloads on Modal's serverless GPU cloud: deploy models as auto-scaling APIs, run batch jobs, and schedule tasks with pay-per-second GPU pricing.

Build lightweight AI agents with HuggingFace Smolagents — use CodeAgent (writes Python to act) or ToolCallingAgent (JSON tool calls), add built-in or custom Tools, orchestrate multi-agent pipelines with ManagedAgent, and run locally or via HF Inference API.

Trains, evaluates, exports, and runs inference for NVPanoptix3D models that perform panoptic 3D scene reconstruction from posed RGB images, producing 3D panoptic segmentation with occupancy completion.

Run 250+ AI apps from the command line: generate images and videos, call LLMs, search the web, create 3D models, and automate Twitter posts.

Runs the open-source LLaVA vision-language model for image understanding, captioning, visual question answering, and multi-turn image conversations, including setup, inference, and training guidance.

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.

Trains, evaluates, exports, prunes, quantizes, retrains, and runs inference for TAO OCRNet models for scene text recognition from cropped text-region images, supporting CTC and attention-based decoders.

Train, evaluate, export, and run inference for monocular depth estimation models using Metric Depth Anything v2 or Relative Depth Anything architectures via the TAO toolkit.

Train, evaluate, export, and run inference on TAO action-recognition models for classifying temporal actions in video clips using RGB, optical flow, or joint input.

Build, fit, validate, and compare Bayesian models using PyMC's modern API, including hierarchical models, MCMC sampling, variational inference, posterior predictive checks, and model comparison.

Provides isolated, agent-native sandboxes for code execution, live preview URLs, browser automation, and access to 50+ tools via CLI or HTTP, with no SDK or API keys required.

Build video analytics pipelines using NVIDIA DeepStream SDK 9.0 with Python pyservicemaker API, including GStreamer-based video processing, TensorRT inference integration, object detection/tracking, and Kafka/message broker integration.

Generates synthetic body MRI volumes using NVIDIA's NV-Generate-CTMR rflow-mr model. Wraps the upstream diffusion inference pipeline with config staging, output validation, and NIfTI volume summarization.

Trains, evaluates, exports, prunes, quantizes, retrains, and runs inference for OCDNet scene text detection models using TAO, detecting arbitrary-oriented text regions in natural images.

Trains, evaluates, and runs inference for Mask Auto-Label (MAL) weakly-supervised segmentation models using ViT-MAE backbones with minimal point or box annotations.

Trains, evaluates, exports, and runs inference for Visual ChangeNet models used in AOI defect detection, comparing image pairs for PASS/NO_PASS classification or change-segmentation masks.

Estimate cell state transitions from unspliced/spliced mRNA dynamics using scVelo, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data.

Discovers and uses scientific datasets, models, blog posts, and interactive demos from a curated catalog for AI/ML work in domains like biology, chemistry, physics, and genomics.

Learn best practices for writing effective AI video generation prompts, covering shot types, camera movements, lighting, style keywords, and model-specific tips for Veo, Seedance, Wan, Grok, and others.

Quantize large language models to 4-bit with minimal accuracy loss using GPTQ, enabling deployment of 70B+ models on consumer GPUs with 4× memory reduction and 3-4× faster inference.

Self-hosted OpenAI-compatible LLM router — smart tier-based routing, ZK-stamped routing decisions, mode overrides, free OpenRouter at install via the Birth bot. Save 60-80% on inference costs by routing to the cheapest capable model across 12+ OpenRouter models.

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

Trains, evaluates, and runs inference for BEVFusion multi-sensor 3D object detection models that fuse LiDAR and camera data in bird's-eye-view space for autonomous driving.

Trains, evaluates, exports, quantizes, and runs inference for a Mask Grounding DINO model for open-set instance segmentation guided by text prompts.

Compress large language models by 40-60% with minimal accuracy loss using one-shot pruning techniques like Wanda and SparseGPT, enabling faster inference and deployment on constrained hardware.

Benchmarks systems on the Abstraction and Reasoning Corpus (ARC) by requiring inference of abstract transformation rules from few input-output grid demonstrations and application to novel test cases, reporting the fraction of tasks solved.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Train, evaluate, export, quantize, and run inference for a Deformable DETR 2D object detection model using TAO, with deformable attention for efficient multi-scale feature processing.