Results for “pipeline parallel”

Build a Python workflow for empirical research, from data cleaning and statistical checks to estimation, robustness checks, and paper-ready tables and figures. Economics is the default, with additional modes for epidemiology, public health, and machine learning for causal inference.

• Building an end-to-end empirical analysis workflow in Python
• Replicating an applied economics paper
• Producing regression tables and event-study plots

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.

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

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.

The English summary is being prepared. Showing the original description.

The systematic orchestration of AI-powered marketing workflows that combine content generation, approval processes, multi-channel distribution, and quality gates into cohesive automation systems. This skill integrates AI generation tools (Jasper, Claude, GPT) with automation platforms (Zapier, Make, n8n) and marketing systems to build scalable content pipelines. It focuses on maintaining brand consistency, implementing rigorous quality gates, and balancing automation with strategic human oversight. Key capabilities include designing parallel approval flows, monitoring costs, and architecting "invisible" automation that enhances productivity without sacrificing quality.Use when "AI workflow, automate content, content automation, workflow automation, AI pipeline, automated marketing, content distribution automation, approval workflow, scale content production, AI orchestration, automation, workflow, ai-orchestration, content-pipeline, approval-workflow, multi-channel, quality-gates, cost-control" mentioned.

The English summary is being prepared. Showing the original description.

Bitbucket Pipelines migration to GitHub Actions — syntax mappings and the migration report template for Pipelines, Pipes, parallel steps, branch/pull-request workflows, deployments, variables. Load with `migration-core` when migrating Bitbucket Pipelines sources to GitHub Actions.

The English summary is being prepared. Showing the original description.

Use when the user asks for a multi-agent .NET code review - five parallel reviewers (correctness, performance, security/observability, data/messaging/integration, generalist) plus an adversarial maintainer that refutes weak findings. Requires the review agent roles registered by scripts/install-codex.sh. Keywords: dotnet review pipeline, multi-agent review, parallel reviewers, maintainer pushback, review this branch, cynical review.

The English summary is being prepared. Showing the original description.

Fornece treinamento distribuído de LLM nativo do PyTorch usando torchtitan com paralelismo 4D (FSDP2, TP, PP, CP). Use para fazer pré-treinamento de Llama 3.1, DeepSeek V3 ou modelos customizados em escala de 8 a 512+ GPUs com Float8, torch.compile e checkpoint distribuído.

The English summary is being prepared. Showing the original description.

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

The English summary is being prepared. Showing the original description.

Build Python workloads on Modal for cloud execution, including GPU model training and inference, web APIs, scheduled jobs, and parallel batch processing. Configure container environments, persistent storage, and automatic scaling through the Modal SDK.

• Serving an AI model through a web API
• Running model training or fine-tuning on cloud GPUs
• Processing independent batch inputs in parallel

Design automated build, test, and deployment workflows for GitHub Actions, GitLab CI/CD, and Jenkins. Covers job ordering, dependency caching, secret handling, and gradual releases that use health checks before expanding deployment.

• Automating builds, tests, and deployments
• Reducing pipeline time with caching and parallel jobs
• Planning gradual releases and rollbacks

Review source code without running it to identify potential security vulnerabilities. Findings include severity, confidence, attack scenarios, and suggested fixes, delivered as JSON for further triage and Markdown for human review.

• Review source code for potential vulnerabilities
• Focus a scan using a threat model
• Prepare findings for further triage

Build workflows on OpenServ where multiple AI agents share tasks and pass results between steps. Examples cover research, writing, and image creation, with guidance on finding agents, setting dependencies, and connecting sequential or parallel work.

• Connect research and writing agents
• Build a research-to-image content pipeline
• Combine results from parallel tasks

Revise formulaic academic prose through staged vocabulary and structure edits while checking that citations, statistics, and technical terms remain intact. Choose sections and editing intensity, compare changes, and review progress before accepting the revised manuscript.

• Revising formulaic wording in an academic draft
• Editing only the discussion and conclusion
• Checking that citations and statistics survive revisions

Build causal inference analyses to estimate intervention effects using templates drawn from Causal Inference: The Mixtape. Adapt code across Python, R, and Stata, with checks for method assumptions and guidance on language-specific packages and limitations.

• Implement a difference-in-differences analysis
• Set up an event study and check parallel trends
• Build instrumental variable or discontinuity models

Manage long or multi-part agent tasks by defining observable completion criteria before work begins. Break work into deliverables, run approved checks, and verify recorded evidence again before reporting which requirements are met or still need attention.

• Defining completion criteria for long autonomous tasks
• Finding omissions in work returned half-finished
• Coordinating parallel deliverables and integration checks

Summon shadow clones: genjutsu's full-scale pipeline for a whole website or web app, from scratch or as a full redesign. Harvests the client's real material, researches in parallel, lets Impeccable lead the direction and genjutsu the motion, builds the pages with parallel agents, then loops fixes, verdicts and a cold-eyes art director until only minor issues remain, the round cap of the chosen tier is reached, or a round fixes nothing. Announces its cost first and asks twice. Web. Needs a host that can spawn subagents.

The English summary is being prepared. Showing the original description.

Constructs secure, efficient CI/CD pipelines with supply chain security (SLSA), monorepo optimization, caching strategies, and parallelization patterns for GitHub Actions, GitLab CI, and Argo Workflows. Use when setting up automated testing, building, or deployment workflows.

The English summary is being prepared. Showing the original description.

Python-based workflow manager for reproducible, scalable pipelines. Define rules with file-based dependencies; Snakemake resolves execution order and parallelism. Runs local, SLURM, LSF, AWS, GCP via profiles; per-rule conda/Singularity envs. For NGS pipelines, ML training, and multi-step file processing. Use Nextflow for Groovy dataflow or nf-core integration.

The English summary is being prepared. Showing the original description.

Fan out a one-shot or flat parallel batch of cc-fleet PROVIDER subagents (headless `cc-fleet subagent`) that return a result — DeepSeek / GLM / Kimi / Qwen / MiniMax, or a Codex/Claude subscription. Trigger ONLY to delegate a task to a cc-fleet provider worker (parallel research, bulk per-file work, a specialized model). Do NOT trigger for a multi-phase pipeline (that is /cc-fleet:workflow), for ordinary local shell/coding, or for editing or researching cc-fleet's own code.

The English summary is being prepared. Showing the original description.

Expert guide for parallel tool execution, MCP batching (vibes_batch), asynchronous Promise.allSettled pipelines, subagent concurrent fan-out, and latency-optimized tool calling loops / Panduan ahli eksekusi tool paralel dan batching MCP.

The English summary is being prepared. Showing the original description.

Run the Yuzu full governance pipeline on a commit range. Produces Gate 1 Change Summary, then orchestrates Gates 2-6 as parallel agent fan-outs with pre-written prompt preambles. Use when the user says "/governance <range>" or "full governance" or asks to run the multi-gate review pipeline on a PR/commit set.

The English summary is being prepared. Showing the original description.

Canonical patterns for writing custom MSBuild targets. Only activate in MSBuild/.NET build context. USE FOR: diagnosing and fixing custom target authoring anti-patterns, reviewing MSBuild target definitions for correctness, diagnosing broken SDK target chains across files (e.g., Directory.Build.targets silently redefining SDK targets), fixing targets that replace CompileDependsOn instead of extending it with $(CompileDependsOn), fixing query targets that return stale results due to Outputs vs Returns misuse, fixing missing Inputs/Outputs causing unnecessary rebuilds, fixing missing FileWrites registration. Covers DependsOnTargets vs BeforeTargets vs AfterTargets, the Build→CoreBuild three-level pattern, hooking into the build pipeline, the $(XxxDependsOn) chain-extension pattern. DO NOT USE FOR: incremental build tuning (use incremental-build), parallelization (use build-parallelism), general anti-patterns (use msbuild-antipatterns), non-MSBuild build systems.

The English summary is being prepared. Showing the original description.

Use when a task needs a small, throwaway multi-agent fan-out (a couple of parallel workers plus a review pass) in ANY project — trigger phrases "spawn a few parallel agents", "fan out", "quick worker team" — without the full /startcycle-graph contract, no .agents/graph.md bootstrap, no state.json schema, no persistent files. Roles run on the session model unless `.aos/pipeline.json` overrides one (an external CLI can take the worker step) and portable across machines that may not have Antigravity/OpenCode/Codex installed.

The English summary is being prepared. Showing the original description.

Authors bioinformatics pipelines in WDL (Workflow Description Language) run by Cromwell or miniwdl, targeting the GATK/Broad and Terra/AnVIL/BioData Catalyst cloud ecosystem, with tasks, workflows, scatter-gather parallelism, structs, and a runtime block that sizes the cloud VM. Use when deciding to target Terra/AnVIL/GATK/WARP (chosen for the ecosystem, not the language); sizing runtime disks dynamically for a fresh-per-task cloud VM (ceil(size(f)*factor)+buffer); choosing preemptible vs on-demand VMs by task length and idempotency; picking Cromwell (production, cloud, call-caching) vs miniwdl (local dev, miniwdl check linting, readable errors); enabling and debugging call-caching silent-miss modes; pinning Docker by digest for reproducibility and cache stability; or scattering an array for parallel fan-out.

The English summary is being prepared. Showing the original description.