'cpu' 검색 결과

Compress screen recordings on Apple Silicon Macs using dedicated video hardware. Choose quality settings for sharing or archiving, inspect video properties, and check the resulting file size and storage savings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Shrink screen recordings for chat or email
• Keep text legible in shared tutorial recordings
• Choose higher quality for archived recordings

Use Dask to process tables, numerical arrays, and file collections in pieces across CPU cores or machines. Helps choose data structures, size memory-friendly chunks, coordinate dependent tasks, and diagnose slow or memory-heavy workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Aggregate CSV or Parquet files that exceed available memory
• Process large scientific arrays in chunks
• Clean JSON records and logs before analysis

Control and inspect a live Chrome browser through Chrome DevTools MCP. Automate page interactions, capture screenshots, inspect errors and network requests, and record performance data to investigate slow loading and unexpected layout changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Automating navigation and form entry
• Capturing page screenshots and text snapshots
• Investigating console errors and failed requests

Choose SGLang Diffusion settings for a specific model, GPU, and memory budget. Compare generation speed, memory use, and output quality to select command-line options, including CPU offloading, multiple GPUs, caching, and reduced precision.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing generation settings for a specific model and GPU
• Reducing GPU memory use to fit a memory budget
• Comparing performance settings across multiple GPUs

Analyze suspicious Linux ELF executables through file inspection, runtime tracing, and reverse engineering. Identify malware behavior, network destinations, and persistence mechanisms, then organize findings and indicators for investigations involving servers, containers, or cloud infrastructure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Triaging suspicious executables on Linux servers
• Investigating suspected cryptominers
• Analyzing malware found in containers

Build similarity search with FAISS to find nearby matches in large collections of numeric vectors. The skill guides index selection, memory reduction, GPU use, and saving indexes while balancing search speed and accuracy.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find similar items in large vector datasets
• Choose an index for search speed and accuracy
• Reduce memory use for vector search

Plan and configure a shared GKE cluster for multiple teams or environments. Set up namespaces, team permissions, resource limits, and network separation, then use labels and GKE cost allocation to track spending by team.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Design a GKE cluster shared by multiple teams
• Separate development, staging, and production workloads
• Set team permissions and resource quotas

Run batch processing, scientific simulations, and machine learning training on Google Kubernetes Engine. Configure parallel jobs, queues that manage resource access, and distributed computation, with guidance on scaling idle capacity down and recovering from interruptions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run data processing jobs in parallel
• Share computing resources through job queues
• Configure distributed simulations with MPI

Generate Terraform alerts for Cloud Run services, jobs, and worker pools using PromQL, a monitoring query language. Monitor errors, latency, resource usage, job failures, and queue delays, with configurable thresholds and explanations of when each alert triggers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Monitor Cloud Run service errors and latency
• Detect failed batch job executions
• Monitor worker pool backlogs and message age

Check mathematical expressions, solve equations, and search bounded ranges for counterexamples using symbolic and numerical libraries. Record assumptions, commands, and results so calculations can be repeated, while keeping computational evidence distinct from general mathematical proof.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking identities and integrals with exact arithmetic
• Searching a defined range for counterexamples
• Cross-checking numerical results at higher precision

Build similarity search with FAISS to find nearby matches in large collections of numeric vectors. The skill guides index selection, memory reduction, GPU use, and saving indexes while balancing search speed and accuracy.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find similar items in large vector datasets
• Choose an index for search speed and accuracy
• Reduce memory use for vector search

Helps adapt machine learning training to multiple GPUs and machines with Ray Train. Covers resource allocation, recovery from saved training states, and Ray Tune searches that compare settings such as learning rate and batch size.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adapt existing PyTorch training to multiple GPUs
• Run HuggingFace training across multiple machines
• Compare learning rates and batch sizes with Ray Tune

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

Build JavaScript or TypeScript applications that run text, image, and audio models in browsers or server runtimes. Guides compatible model selection, GPU or CPU execution, caching, and memory cleanup without requiring a Python server.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add text classification or translation to a browser app
• Implement image classification and object detection
• Transcribe audio using JavaScript

Choose a serving container for models deployed on SageMaker. Match the model type to a compatible image, retrieve its address from the AWS catalog, and check regional availability, CPU or GPU variants, and required host settings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a container for an LLM deployment
• Select images for embeddings and rerankers
• Check regional image addresses and GPU compatibility

Search Hugging Face Hub for models, datasets, papers, and AI apps. Inspect documentation, use hosted apps for image generation or transcription, and run or schedule code on cloud CPUs and GPUs through an MCP server connection.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare models for a specific task
• Find training datasets
• Generate images or transcribe audio with Spaces

Sets up AFL++ to test C/C++ programs with varied generated inputs, a technique called fuzzing. Covers running tests across CPU cores, monitoring progress, reducing input collections, and reproducing crashes for investigation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running C/C++ fuzzing across multiple CPU cores
• Exploring further after libFuzzer progress stalls
• Monitoring fuzzing progress and stability

Plan when an agent’s tool environments are created, kept available, released, and restored. Estimate peak concurrency, resource use during work and waiting, total task duration, and cost across model calls, tool execution, validation, and retries.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Estimating peak concurrent agent environments
• Comparing environment retention and recreation
• Assessing cold starts and shared environment pools

Optimize .NET loops with SIMD, which processes multiple values in one operation, or review existing SIMD code. Check behavioral equivalence, memory safety, platform fallbacks, and benchmarks to establish whether the optimization is correct and worthwhile.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Optimize numeric loops with SIMD
• Review existing vectorized code for correctness
• Test boundary lengths and overlapping buffers

Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Host-side DOCA UROM library (doca_urom_*): offload an HPC / UCX / MPI application's remote memory operations (puts, gets, atomics, collectives) from the host CPU onto a BlueField DPU. Trigger on "MPI all-reduce burning host CPU", "push UCX traffic onto the BlueField", "first doca_urom call returns NOT_PERMITTED", or "host library and DPU service look out of sync", even without naming DOCA UROM. An offload needs both halves: this host library and the UROM Service on the DPU (doca-urom-svc), which owns deploying that container. Covers creating UROM Service contexts (doca_urom_service_*) and Worker contexts (doca_urom_worker_*) that run plugins on the DPU, discovering plugins via doca_urom_service_get_plugins_list, progressing completions, and DOCA_ERROR_* from doca_urom_* calls. Route elsewhere for UROM Service deployment on the DPU side, MPI / UCX collective algorithm design, and RDMA / RoCE / IB substrate bring-up.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill when the user is measuring GPU-kernel-initiated RDMA WRITE latency through doca-gpunetio — building and running the `gpunetio_ib_write_lat` client + server pair under `doca/tools/gpunetio_ib_write_lat/`, checking GPU-NIC pairing, reading the half-iter / full-iter / CUDA-side usec columns, characterizing median / p99 / jitter for a real-time control loop, picking GPUNetIO vs GPI vs CPU-initiated `perftest`, or weighing the latency-vs-batching trade-off. Trigger even without 'GPUNetIO' or 'ib_write_lat': 'GPU kernel RDMA latency benchmark', 'how fast can a CUDA kernel post a WRITE', 'p99 RDMA latency on H100 + ConnectX', 'kernel-launched WR tail latency', or 'compare GPU-init vs CPU-init perftest'. Route elsewhere for bandwidth runs (doca-gpunetio-ib-write-bw), the GPI surface (doca-gpi), library debugging (doca-gpunetio), or DOCA install.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill for hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without host CPU mediation. Covers picking GPI vs doca-gpunetio, the doca_gpi / domain / channel object model, the GPU-side handle handoff (doca_gpu_gpi_channel*), attaching GPU memory to a GPI domain, the domain and channel attribute objects, and debugging DOCA_ERROR_* from doca_gpi_* calls. Trigger even when the user does not explicitly mention "DOCA GPI" — implicit phrasings include "my CUDA kernel needs to post RDMA directly from GPU memory", "DOCA_ERROR_* from doca_gpi_gpu_channel_get", "how do I hand a GPU handle to my CUDA kernel", "how many channels can a GPI domain hold", or "GPU kernel driving RDMA without the host CPU on the path". Refuse and route elsewhere for the doca-gpunetio Send/Receive surface, the doca-rdma queue lifecycle, DPA-side initiation (doca-rdmi), or the CUDA programming model — those belong to other skills.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill when the user is measuring the host or DPU-CPU control-plane rate of a DOCA Flow pipeline with doca_flow_perf — picking a JSON policy from configs/, choosing the DPDK or DOCA backend, running the single-iteration smoke then the iterative eval loop, interpreting per-iteration CPU cycles and num_pushed / num_failed, or capturing the four-tuple (DOCA version, BlueField/firmware, JSON policy, worker/queue/burst config) that makes a Kops/sec number defensible. Trigger even when the user does not explicitly mention "doca-flow-perf" — typical implicit phrasings include "how many rules per second can my BlueField insert", "5-tuple hairpin rule rate", "Kops/sec for steering", "flow-perf number does not match release notes", "DPDK vs DOCA benchmark", or "rule-install variance too high". Refuse and route elsewhere for optimizing a live Flow app (doca-flow-tune), the DPA-offloaded path (doca-flow-dpa-perf), dataplane throughput or latency, or library-internal pipe semantics — those belong to other skills.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.