528 个 · 按相关度排序
Prepare the runtime for Isaac for Healthcare workflows by checking host requirements and setting up dependencies. Verify that workflows can be listed and their definitions pass checks, and identify the first setup failure requiring attention.
中文简介正在准备中。当前显示英语简介。
Customize Jetson and Tegra power modes in BSP files, the device's system software configuration. Adds, removes, or edits nvpmodel profiles, adjusts frequency limits, changes the boot default, and guides deployment of the updated configuration.
中文简介正在准备中。当前显示英语简介。
Install a Holoscan SDK 5.x CUDA 13 development container after checking the exact release and host compatibility. Verify GPU access, run installed examples, and check the SDK version and Python API.
中文简介正在准备中。当前显示英语简介。
Build and run a benchmark for RDMA WRITE, a direct memory transfer initiated by a CUDA kernel. Check GPU and network adapter pairing, interpret timing columns, and assess median latency, p99, and timing variation.
中文简介正在准备中。当前显示英语简介。
DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin or 5-tuple-to-queue questions even when "DOCA Flow" is not named. Remote or non-C++ control over gRPC belongs to doca-flow-grpc-server. Also covers pipe validation before hardware programming, Flow/DOCA version match, and Flow API errors. First app: follow the local bundle (doca-setup, doca-programming-guide, doca-flow, doca-public-knowledge-map). Stage 1 pull nvcr.io/nvidia/doca/doca (NGC catalog tag, never invent); Stage 2 needs a real NIC. Then ls samples inside the container; never emit main.c, a Dockerfile, or hand-typed -l flags. Route software-only host pipelines, plain DPDK `rte_flow`, kernel TC, OVS, BFB bring-up, and DPU OS installation elsewhere. DPU OS installation is destructive and always requires explicit confirmation.
中文简介正在准备中。当前显示原文说明。
Get guidance on installing CUDA-Q, writing quantum processing functions, and choosing CPU or GPU simulation targets. Also covers connecting to quantum processors, running a Bell-state example, and selecting approaches for execution across multiple devices.
中文简介正在准备中。当前显示英语简介。
Fine-tune Parakeet TDT v2 on clinical vocabulary using NeMo, then compare key-term error rates before and after training. The results guide whether to keep the model, expand the dataset, or prepare it for deployment.
中文简介正在准备中。当前显示英语简介。
Build English clinical speech-recognition benchmarks by selecting medical terms, checking pronunciations, and generating synthetic audio. Outputs include audio files and a NeMo manifest, a structured file listing recordings and metadata, ready for a separate scoring stage.
中文简介正在准备中。当前显示英语简介。
Extend an existing grover_base model with a new decoder that reconstructs molecular structure strings, then continue pretraining on your corpus. The workflow validates inputs, rebuilds vocabulary components, and records the conversion and training outputs.
中文简介正在准备中。当前显示英语简介。
Generate molecular predictions from a CSV of SMILES strings, a text notation for molecular structures, using a finetuned KERMT model. Validate inputs, clean data, compute molecular features, and return predictions with execution logs and a replay command.
中文简介正在准备中。当前显示英语简介。
Start a cuOpt REST server and build Python or curl clients to submit routing and optimization problems. Follow result polling, translate Python API field names into REST fields, and diagnose rejected requests.
中文简介正在准备中。当前显示英语简介。
Pretrain a new KERMT chemistry model from a molecular corpus, starting with random weights. The skill validates the data, builds fresh vocabularies, estimates runtime, and launches containerized training with logs and records for reproducing the run.
中文简介正在准备中。当前显示英语简介。
An engineering-grade marketing system organized around two surface modes — a deep black canvas for hero and footer chapters and a flat paper-white canvas for body content — connected by a single, almost violently saturated NVIDIA Green accent that carries every CTA, every active tab, and the small decorative corner squares that mark out cards. The system is unapologetically angular: 2px radius across every surface, tight bold sans-serif typography in NVIDIA's proprietary EMEA cut, and a hairline gray rule that separates dense multi-column technical content. There is no decorative gradient, no atmospheric mesh, no soft drop shadow — just black, white, gray, and green stacked into a structured editorial grid that scales from product cards to massive industry landing pages without bending its rules.
中文简介正在准备中。当前显示原文说明。
语音转文字 (ASR) (语音转文字 (ASR / 语音识别 / Speech-to-Text) 应用工程 (从业者视角) — 选型、集成、优化语音转文字能力，尤其面向移动端、低成本、快速识别的场景。覆盖: (a) 引擎/API 地图 — 云端 API(OpenAI gpt-4o-transcribe / Whisper API、Deepgram、AssemblyAI、Google / Azure / AWS Transcribe、讯飞、字节火山、阿里、腾讯、百度) vs 开源模型(Whisper / faster-whisper / whisper.cpp / distil-whisper、NVIDIA NeMo Parakeet / Canary、阿里 FunASR / Paraformer / SenseVoice、Moonshine、Vosk、Kaldi / k2 / icefall) vs 端侧·移动 SDK(whisper.cpp + CoreML / Metal、iOS Speech framework、Android SpeechRecognizer、Picovoice、SenseVoice 端侧); (b) 准确率(WER / CER) × 延迟(RTF / 流式) × 成本 三角权衡与选型决策树; (c) 成本优化 playbook — 端侧免费 / 批量折扣 / VAD 裁静音 / 量化(int8 / ggml) / 蒸馏 / 自托管 break-even; (d) 移动端集成 — 端侧 vs 云、流式 vs 批量、断点检测(endpointing)、隐私 / 离线; (e) 后处理 — 标点 / 数字规整(ITN) / 说话人分离(diarization) / 时间戳。学派分歧: 云 API vs 端侧自托管、通用大模型(Whisper) vs 专用流式(RNN-T / Conformer)、闭源 API vs 开源、准确率派 vs 成本派、英文优先 vs 中文 ASR(FunASR / SenseVoice / 讯飞)。不含: 文字转语音(TTS / 语音合成，方向相反)、声纹识别 / 说话人验证为主业、语音 agent / 对话式 AI、ASR 模型训练科研深水区。) Master OS — automated mastery of 语音转文字 (ASR / 语音识别 / Speech-to-Text) 应用工程 (从业者视角) — 选型、集成、优化语音转文字能力，尤其面向移动端、低成本、快速识别的场景。覆盖: (a) 引擎/API 地图 — 云端 API(OpenAI gpt-4o-transcribe / Whisper API、Deepgram、AssemblyAI、Google / Azure / AWS Transcribe、讯飞、字节火山、阿里、腾讯、百度) vs 开源模型(Whisper / faster-whisper / whisper.cpp / distil-whisper、NVIDIA NeMo Parakeet / Canary、阿里 FunASR / Paraformer / SenseVoice、Moonshine、Vosk、Kaldi / k2 / icefall) vs 端侧·移动 SDK(whisper.cpp + CoreML / Metal、iOS Speech framework、Android SpeechRecognizer、Picovoice、SenseVoice 端侧); (b) 准确率(WER / CER) × 延迟(RTF / 流式) × 成本 三角权衡与选型决策树; (c) 成本优化 playbook — 端侧免费 / 批量折扣 / VAD 裁静音 / 量化(int8 / ggml) / 蒸馏 / 自托管 break-even; (d) 移动端集成 — 端侧 vs 云、流式 vs 批量、断点检测(endpointing)、隐私 / 离线; (e) 后处理 — 标点 / 数字规整(ITN) / 说话人分离(diarization) / 时间戳。学派分歧: 云 API vs 端侧自托管、通用大模型(Whisper) vs 专用流式(RNN-T / Conformer)、闭源 API vs 开源、准确率派 vs 成本派、英文优先 vs 中文 ASR(FunASR / SenseVoice / 讯飞)。不含: 文字转语音(TTS / 语音合成，方向相反)、声纹识别 / 说话人验证为主业、语音 agent / 对话式 AI、ASR 模型训练科研深水区。: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. Trigger this skill when the user works on 语音转文字 (ASR / 语音识别 / Speech-to-Text) 应用工程 (从业者视角) — 选型、集成、优化语音转文字能力，尤其面向移动端、低成本、快速识别的场景。覆盖: (a) 引擎/API 地图 — 云端 API(OpenAI gpt-4o-transcribe / Whisper API、Deepgram、AssemblyAI、Google / Azure / AWS Transcribe、讯飞、字节火山、阿里、腾讯、百度) vs 开源模型(Whisper / faster-whisper / whisper.cpp / distil-whisper、NVIDIA NeMo Parakeet / Canary、阿里 FunASR / Paraformer / SenseVoice、Moonshine、Vosk、Kaldi / k2 / icefall) vs 端侧·移动 SDK(whisper.cpp + CoreML / Metal、iOS Speech framework、Android SpeechRecognizer、Picovoice、SenseVoice 端侧); (b) 准确率(WER / CER) × 延迟(RTF / 流式) × 成本 三角权衡与选型决策树; (c) 成本优化 playbook — 端侧免费 / 批量折扣 / VAD 裁静音 / 量化(int8 / ggml) / 蒸馏 / 自托管 break-even; (d) 移动端集成 — 端侧 vs 云、流式 vs 批量、断点检测(endpointing)、隐私 / 离线; (e) 后处理 — 标点 / 数字规整(ITN) / 说话人分离(diarization) / 时间戳。学派分歧: 云 API vs 端侧自托管、通用大模型(Whisper) vs 专用流式(RNN-T / Conformer)、闭源 API vs 开源、准确率派 vs 成本派、英文优先 vs 中文 ASR(FunASR / SenseVoice / 讯飞)。不含: 文字转语音(TTS / 语音合成，方向相反)、声纹识别 / 说话人验证为主业、语音 agent / 对话式 AI、ASR 模型训练科研深水区。 problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「语音转文字」「语音识别」「asr」「speech to text」「stt」
中文简介正在准备中。当前显示原文说明。
Otimiza inferência de LLM com NVIDIA TensorRT para máxima vazão e latência mínima. Use para implantação em produção em GPUs NVIDIA (A100/H100), quando você precisa de inferência 10-100x mais rápida que PyTorch, ou para servir modelos com quantização (FP8/INT4), batching em voo e escalabilidade multi-GPU.
中文简介正在准备中。当前显示原文说明。
NVIDIA DeepStream model-import guidance for bringing vision models from Hugging Face or NVIDIA NGC into DeepStream pipelines with export, TensorRT build, and benchmark steps.
中文简介正在准备中。当前显示原文说明。
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
Manage the credentials Arize uses to call LLM providers such as OpenAI and Anthropic. Create, inspect, update, or delete connections, configure allowed models and authentication methods, and retrieve connection IDs for use in evaluations.
中文简介正在准备中。当前显示英语简介。
Set up LLM serving with structured responses, including JSON and outputs restricted to specified patterns. Covers reusing shared prompt calculations, tool calling, and multi-turn conversations through SGLang, with examples for server setup and application integration.
中文简介正在准备中。当前显示英语简介。
Turn text into embeddings, numeric representations of meaning, through 9Router. Choose a model and process individual texts or batches to prepare data for meaning-based search, similarity comparisons, or RAG systems that retrieve reference material.
中文简介正在准备中。当前显示英语简介。
Run OpenShell’s Release Canary checks to verify that published development packages and Helm charts install and support basic sandbox operations. Use workflow logs and local Kubernetes reproduction steps to investigate failures before a public release.
中文简介正在准备中。当前显示英语简介。
Build LLM serving workflows that produce JSON or other required formats. The skill covers reusing computation for shared prompts, tool calls, and ongoing conversations, with examples for server setup and structured output.
中文简介正在准备中。当前显示英语简介。