'parallel' 검색 결과

Delegate a self-contained coding task to Codex CLI from another agent using ChatGPT subscription authentication. Run independent implementation, request a second opinion, or verify changes, with separate working copies for parallel tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Delegating a clearly scoped feature or bug fix
• Running independent implementation tasks in parallel
• Getting a second opinion on code

Isolate parallel coding tasks with Git worktrees, separate working folders with their own branches. The skill guides environment setup, dependency installation, change review, merging, and cleanup so each task has a dedicated workspace.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare separate working folders for parallel coding tasks
• Set up dependencies and environment files in a new worktree
• Review and merge completed changes

Assign independent bugs or test failures to separate agents that work at the same time. Define each agent’s scope and expected report, then check for conflicting changes and run the full test suite before integrating fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating test failures with unrelated causes
• Fixing independent problems in separate subsystems
• Defining focused tasks for multiple agents

Coordinate large code refactors or rewrites across multiple agents. It organizes parallel analysis, assigns clear file ownership, schedules work around dependencies, and checks individual changes and their integration against agreed requirements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Refactoring code across many files
• Dividing implementation work among multiple agents
• Planning changes across dependent modules

Review a git diff or selected files with parallel agents to find behavior regressions, security risks, reliability problems, and compatibility or test gaps. Receive filtered, evidence-backed findings and prioritized recommendations without changing files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check changed code for unintended behavior
• Review security and privacy risks
• Find performance and reliability problems

Coordinates a named team of Codex workers with concrete responsibilities and shared progress records. It selects available collaboration tools, manages communication and separate working copies when needed, and handles integration, team archival, and cleanup after the work ends.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Splitting related implementation work across cooperating agents
• Investigating several aspects of a clearly defined problem
• Inspecting team progress and member responsibilities

Build and train reinforcement learning agents, which learn actions through rewards. The skill guides custom environment creation, parallel simulation tuning, integration with existing environments, and policy development for image or sequential observations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train agents in existing reinforcement learning environments
• Create custom simulation environments
• Tune parallel simulations for higher throughput

Check CPU cores, GPUs, available memory, and disk space before demanding computing tasks. Save a JSON report with recommendations for parallel workers, GPU use, and processing data in chunks when memory is limited.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking memory before analyzing large datasets
• Identifying available GPUs before model training
• Choosing worker counts for parallel file processing

Tune adaptive behavior in an instrumented NeMo Relay application using runtime data. Configure tool parallelism, prompt caching, and state storage, then compare changes against a baseline to check latency, correctness, and failure rates.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Evaluate adaptive behavior using runtime telemetry
• Tune tool parallelism against a baseline
• Evaluate prompt-cache planning

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

Configure and validate communication overlap in Megatron-Bridge for MoE models, which distribute work among expert networks. Check compatibility, compare training speed, and investigate regressions across standard dispatch, DeepEP, HybridEP, and delayed weight-gradient computation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Enable expert communication overlap in MoE training
• Check compatibility before using DeepEP or HybridEP
• Compare plain overlap and delayed weight-gradient computation

Diagnose GPU out-of-memory errors during Megatron Bridge training and choose memory reduction settings. Covers fragmentation, LoRA input storage, recomputation, parallelism changes, and CPU offloading, explaining compatibility limits and potential tradeoffs between memory use and training throughput.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating GPU out-of-memory errors during training
• Reducing retained inputs in LoRA training
• Estimating memory needs before a large training job

Configure Megatron-Bridge to overlap communication with computation during distributed training. Review settings for tensor, data, and pipeline parallelism, check activation requirements, and use included tests to investigate configuration issues or throughput regressions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Enable communication overlap in distributed training
• Check why tensor parallel overlap is inactive
• Investigate slower training after configuration changes

Choose Megatron Bridge training configurations for a model, GPU allocation, and training goal. Get starting commands and parallel processing adjustments, with clear distinctions between changes that affect learning behavior, execution tuning, and benchmark-only settings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a starting configuration for pretraining or fine-tuning
• Adapt parallel processing settings to available GPUs
• Compare training and throughput benchmark configurations

Plan and tune training for vision-language models that use MoE, a mixture of expert networks, in Megatron Bridge. Compares FSDP and 3D parallel training, with guidance on memory use, batch sizes, and performance checks using realistic image inputs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a parallel training approach for a new model
• Investigating training failures and out-of-memory errors
• Comparing performance with realistic image inputs

Coordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system areas. Use when debugging production incidents, slow API performance, multi-system integration failures, or complex bugs where the root cause is unclear and multiple plausible theories exist; when serial troubleshooting is too slow; or when multiple investigators can divide root-cause analysis work. Provides structured phases for problem decomposition, thread assignment, sync points with Continue/Pivot/Converge decisions, and final report synthesis.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Patterns for parallel subagent execution using the Agent tool (formerly Task). Use when coordinating multiple independent tasks, spawning dynamic subagents, or implementing features that can be parallelized.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill to run multiple Simulink simulations in parallel with parsim, batchsim, and DesignStudy. TRIGGER when: user asks for parameter sweep, sweeping/varying parameters across simulations, Monte Carlo study, batch simulation, running multiple simulations, parallel simulations, large-scale multiple simulations, any task involving repeated simulations with different parameter values, user mentions having an existing script/function for parameter sweeps, or user wants to migrate from parfor/set_param/for-loop patterns to recommended workflows.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Speed up local parfor, parfeval, or spmd by switching to a thread-based parallel pool. Trigger when a user describes slow or disappointing local parallel performance, even if they don't mention threads. Symptoms: parfor on a laptop/workstation is slower than expected or "only slightly faster than for"; parfor scales poorly with the number of workers; ticBytes/tocBytes, the Parallel Pool dashboard, mpiprofile, or system tools show large per-worker data transfer; large broadcast variables or sliced inputs make iterations slow; opening a process pool dominates a short workload; user mentions serialisation or data transfer overhead. Also trigger on any question about whether code or a function works on a thread pool. For non-pool MATLAB performance work (vectorisation, preallocation, profiling), defer to matlab-optimize-performance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Decision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item) for each item in parallel, then combine". Activates when the coder agent is about to process N items with N LM calls (per-doc summarize, per-query retrieve, per-candidate rank, parallel tool fan-out). Encodes the *when*, *how many at once*, *what to do when one fails*, and *how to reduce* — not the API of any single framework. Cross-framework: LangGraph `Send`, CrewAI parallel tasks / Flow, `asyncio.gather`, `ThreadPoolExecutor`, LlamaIndex batch retrieval.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Parallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel, automatically cross-validate findings, tier by confidence (strong consensus / partial / conflict / insufficient), generate tiered action items with arbitration. Use when user says "多 AI 调研", "交叉验证", "独立共识", "三脑调研", "multi-ai research", "parallel research", "cross-validate", or needs deep research that benefits from internal data + external 2026 consensus. NOT for quick factual Q&A, pure code reasoning, or tasks needing deep project context.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plan, implement, or review dispatching parallel agents work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests dispatching parallel agents work.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guides parallel exploration of multiple implementation approaches using git worktrees. Use when facing decisions with multiple valid paths. Triggers on: explore options, compare approaches, parallel exploration.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.