'compute' 검색 결과

Check running experiments, collect logs and result metrics, and summarize progress alongside baseline comparisons. It supports SSH servers, Vast.ai, and Modal, with optional Weights & Biases metrics and cost reporting for the supported compute services.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether remote experiments have finished
• Compare collected metrics with the matching baseline
• Investigate NaN values or diverging training runs

Diagnose unreachable or unhealthy OpenShell gateways and sandbox startup failures. Identify the underlying execution platform, then examine logs, authentication, certificates, and configuration with the matching tools to narrow down the cause.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate gateway connection and health check failures
• Find why a sandbox remains pending or fails to start
• Check Docker or Podman runtime and image problems

Train Mixture of Experts models, which activate selected specialist networks for each input. The skill guides architecture, input routing, workload balancing, and GPU distribution using DeepSpeed or HuggingFace, with examples for training configuration and inference optimization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a model that activates only selected expert networks
• Balancing workloads across expert networks
• Distributing experts across multiple GPUs

Find and run local AI models with llama.cpp. Choose GGUF model files and quantization levels that fit available memory, launch a command line session or local server, and test an OpenAI-compatible API on your computer.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find models to run on a local computer
• Choose quantization for available memory
• Launch and test a local OpenAI-compatible API

Find recent arXiv papers on EEG, or brainwave, decoding and brain-computer interfaces. Evaluate candidates using five quality criteria, select the top three, and save structured Chinese and English reviews with paper metadata as Markdown files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracking recent EEG decoding papers
• Finding research on speech decoding from EEG
• Comparing brain foundation model papers

Use Shapely to create points, lines, and polygons from coordinates or text descriptions of shapes. Calculate areas and distances, test spatial relationships, combine or transform shapes, and check or repair invalid geometry, with results returned as JSON.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether a point lies inside a polygon
• Calculate shape areas, perimeters, and distances
• Combine shapes or extract overlapping regions

Use Pint to convert measurements, calculate with units, and check whether units describe compatible physical quantities. It also breaks quantities into values and units, simplifies compound units, and returns calculation results as JSON.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Converting measurements between unit systems
• Calculating with mixed units
• Checking the dimensional consistency of formulas

Automates computational chemistry through Rowan's Python API, including molecular property prediction, structure optimization, and protein–ligand binding predictions. Submits cloud calculations, handles batches of molecules, tracks workflow status, and retrieves results without a local compute cluster.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Batch prediction of molecular pKa values in Rowan
• Optimizing molecular structures and comparing conformers in Rowan
• Predicting protein–ligand binding and complex structures in Rowan

Build image and video AI systems for object detection and segmentation, which identifies separate image regions. The skill covers custom model training, dataset pipelines, inference optimization, real-time processing, and deployment and monitoring in production.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Developing object detection and image segmentation systems
• Training custom vision models with project data
• Optimizing inference for real-time video processing

Choose an NVSHMEM transport, the communication path between compute nodes, from installed plugins, network evidence, and optional workload analysis. Receive a recommended configuration with minimal environment variables, compatibility evidence, alternatives, and clearly stated unknowns.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a transport compatible with a compute system
• Assessing communication needs in selected CUDA code
• Getting minimal transport selection settings

Evaluate object detection predictions against labeled ground truth with TAO Data Services. Produce class-level precision, recall, accuracy, and AP, a detection quality measure, with CSV results and precision–recall plots for reviewing model performance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Score object detection predictions against ground truth
• Review precision and recall by class
• Generate metrics CSV files and precision–recall plots

Improve MoE training throughput in Megatron Bridge. MoE models divide work among expert networks; this skill identifies memory, communication, and compute bottlenecks, guides controlled configuration comparisons, and validates speed alongside training health.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate training slowdowns after code or configuration changes
• Find memory, communication, and compute bottlenecks
• Compare parallelism, precision, and dispatcher settings

Azure Batch SDK for Java. Run large-scale parallel and HPC batch jobs with pools, jobs, tasks, and compute nodes. Triggers: "BatchClient java", "azure batch java", "batch pool java", "batch job java", "HPC java", "parallel computing java".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks. Triggers: "image analysis", "computer vision", "OCR", "object detection", "ImageAnalysisClient", "image caption".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Routes serverless requests to a compute form factor and the skill that owns it. Applies first to Lambda, API Gateway, EventBridge, Step Functions and event-driven work while the compute, orchestration or integration choice is open — API backends, webhooks, jobs, cron, queue/stream consumers, durable workflows, event routing, Step Functions vs Durable Functions, and Pipes vs native event source mappings for queues and streams. Decides Event Functions on-demand vs Managed Instances, Web Functions, MicroVMs, EventBridge rules/Scheduler/Pipes/bus, HTTP vs REST API. Owns shared Lambda references (cold starts, SnapStart, concurrency, event sources, function URLs, throttling, troubleshooting). Defers to the specialized skill once a request commits to one form factor or service, or describes its defining feature, even unnamed (durable checkpointing and automatic step retries, Firecracker sandbox, managed instances, Node.js server). Not for EC2, ECS/EKS/Fargate or Amplify hosting.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Optimize Apify platform costs through memory tuning, compute unit management, and proxy budgeting. Use when analyzing Apify billing, reducing Actor run costs, or implementing usage monitoring and budget alerts. Trigger with "apify cost", "apify billing", "reduce apify costs", "apify pricing", "apify expensive", "apify budget", "compute units".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Govern Alchemy compute usage and spend with current account evidence, workload attribution, budgets, and reversible optimizations. Use when forecasting or reducing Alchemy cost. Trigger with "Alchemy cost", "Alchemy compute units", or "reduce Alchemy spend".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user asks to run heavy or GPU work on Modal (the cloud compute platform) — writing a Modal function in the workspace, running it with the user's own `modal` CLI + token, and bringing results back. Data-to-compute for jobs too big for the laptop, without a Slurm cluster.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when a task needs an app on the user's own screen — a native desktop application (instrument control software, Origin, GraphPad, ImageJ, a reference manager, a spreadsheet), or a desktop browser window that needs window-level control. Read before the first `computer` call. Covers the observe-act-observe loop, why element indexes go stale, which action to prefer for which control, what "unverified" means and why it must never be reported as success, and the recovery for each error code. Not for page-level web automation (use the browser connector) and not for anything that can be done from the shell.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user asks to run, submit, monitor, or cancel a job on a remote machine over SSH — their own GPU/CPU server, a workstation, or a Slurm cluster ("the cluster", a login node, "my 3090 box", "the compute server"). Picks a saved machine, runs the work directly over SSH (or via Slurm when present), tracks it, and fetches results back into the workspace.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Manage Simulink Real-Time target computers from MATLAB — list available targets, check whether a target is connected, read its lifecycle status, add/remove/rename targets, set IP addresses and credentials, choose the default target, install TLS material, configure a startup application, and run target lifecycle ops (connect, reboot, RTOS update). Use whenever the user asks "which targets are available", "is my target connected", "what's the status of the target", "add a Speedgoat", "switch default target", "change the target IP", "reboot the box", "update the target", or works with `slrealtime.Targets`, `tg = slrealtime`, `addTarget`, `removeTarget`, `getTargetNames`, `getDefaultTargetName`, `setDefaultTargetName`, `connect`, `isConnected`, `status(tg)`, `setipaddr`, `setupTLSCertificate`, `setStartupApp`, `reboot`, `update`, or `slrealtime.testSetup`. Covers Speedgoat target computers and Simulink Real-Time Linux devices.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Reads, queries, and writes bigWig indexed binary signal tracks (coverage, fold-change, conservation, methylation-rate) with pyBigWig (Python) and the UCSC Kent tools (bedGraphToBigWig, bigWigToBedGraph, bigWigInfo, bigWigSummary, bigWigAverageOverBed) and deepTools (multiBigwigSummary, computeMatrix, bigwigCompare). Covers the central trap that a wide query returns a precomputed zoom-level summary (by default the mean, which annihilates narrow peaks) not per-base data, when exact=True/values() is mandatory, the NaN-not-zero gap-handling fork, choosing mean vs max vs sum vs coverage by biological question, and the sorted-bedGraph plus chrom.sizes build requirement. Use when extracting signal at regions, computing mean signal per gene/peak, building a browser track from bedGraph, comparing tracks, or building TSS/gene-body metaprofiles.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.