Results for “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.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency on NVIDIA GPUs (A100/H100).

Optimize MSBuild build parallelism by configuring /maxcpucount, graph build mode, project references, and analyzing binlogs to reduce multi-project solution build times.

Train, evaluate, export, prune, and run inference for PointPillars 3D object detection models from LiDAR point clouds using NVIDIA TAO.

Train, evaluate, distill, quantize, export, and run inference for RT-DETR object detection models using NVIDIA TAO.

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance using TensorBoard.

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Evaluates the robustness and alignment with human judgment of reference-based and reference-free evaluation metrics for machine translation and summarization, particularly under adversarial conditions.

NLVR2: A Visual Reasoning Benchmark for Natural Language

Foundational theory for process-oriented concurrency through synchronous message-passing, applicable to multi-agent coordination and parallel decomposition

Evaluates text-to-image models on spatial relationship accuracy using the VISOR metric, separating object detection from spatial correctness to reveal biases like object priority and merging.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Find adjacent vendors and subs (not top market primes) who fill a capability gap against a displacement target using USASpending flows and SAM entity signals. Use when user defines a teaming gap and wants vault-ready partner shortlist with citations.

PyTorch, TensorFlow, neural networks, CNNs, transformers, and deep learning for production

Task Decomposition

Train, evaluate, export, quantize, and run inference for a TAO OneFormer model that performs panoptic, instance, and semantic segmentation using task-conditioned queries.

Trains, evaluates, exports, and runs inference for Siamese-network-based optical inspection models to detect manufacturing defects and quality issues in image pairs.

Train, evaluate, distill, quantize, export, and run inference for PyTorch-based TAO image classification models with support for multiple backbones.

Train, evaluate, export, and run inference for CenterPose models used in 6-DoF object pose estimation with keypoint regression.

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.

Sequence and choreograph multi-step animations using GSAP timelines, including nesting, labels, position parameter, and playback control.

Trains, evaluates, exports, quantizes, and runs inference for Sparse4D multi-camera temporal 3D object detection and tracking models using TAO.

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

Provides practical guidance for training Mixture-of-Experts Vision-Language Models in Megatron Bridge, comparing FSDP and 3D-parallel approaches with lessons from recent multimodal experiments.

Fine-tune Cosmos Reason video QA models using supervised fine-tuning with FSDP parallelism, including dataset preparation, spec construction, and AutoML support.

Train, evaluate, export, quantize, and run inference on Mask2Former models for panoptic, instance, and semantic segmentation using NVIDIA TAO.

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard.

Generate tensorboard visualizer operations. Auto-activating skill for ML Training. Triggers on: tensorboard visualizer, tensorboard visualizer Part of the ML Training skill category. Use when working with tensorboard visualizer functionality. Trigger with phrases like "tensorboard visualizer", "tensorboard visualizer", "tensorboard".

Expert guidance for architecting, developing, and operating SurrealDB 3, covering SurrealQL, multi-model data modeling, vector search, security, deployment, performance tuning, SDK integration, and ecosystem tools.

Wilkinson, branchline, ratrace, directional couplers, corporate dividers, Rotman lenses for power splitting and beam-forming. TRIGGER: user asks to design, create, or analyze any coupler, splitter, power divider, combiner, or Rotman lens. Invoke BEFORE writing code — class names and design() availability vary per coupler type. SKIP: EM simulation/S-parameter extraction of an existing component (use matlab-analyze-em), building custom non-catalog geometry (use matlab-assemble-pcb-layout), material/stackup setup only (use matlab-manage-pcb-material), cascading multiple components (use matlab-integrate-pcb-circuit).

Use RWKV, a linear-time RNN-Transformer hybrid, for efficient long-context inference and training with constant memory usage.