Skill4Agent
Skill4Agent
All SkillsSearchTools
|
Explore
Skill4Agent
Skill4Agent

AI Agent Skills Directory with categorization, English/Chinese translation, and script security checks.

Sitemap

  • Home
  • All Skills
  • Search
  • Tools

About

  • About Us
  • Disclaimer
  • Copyright

Help

  • FAQ
  • Privacy
  • Terms
Contact Us:osulivan147@qq.com

© 2026 Skill4Agent. All rights reserved.

All Skills

Total 50,633 skills, AI & Machine Learning has 8486 skills

Categories

Showing 12 of 8486 skills

Per page
Downloads
Sort
AI & Machine Learningnvidia/skills

perf-cuda-graphs

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

🇺🇸|EnglishTranslated
8
AI & Machine Learningnvidia/skills

ad-graph-dump

Enable and interpret TensorRT-LLM AutoDeploy FX graph text dumps via AD_DUMP_GRAPHS_DIR. Use when you need before/after graphs per transform, to locate subgraphs, or to confirm a rewrite ran. Paths and behavior are grounded in tensorrt_llm/_torch/auto_deploy (GraphWriter, BaseTransform). Complements ad-add-fusion-transformation.

🇺🇸|EnglishTranslated
8
AI & Machine Learningnvidia/skills

resiliency

Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.

🇺🇸|EnglishTranslated
8
AI & Machine Learningnvidia/skills

perf-tp-dp-comm-overlap

Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

🇺🇸|EnglishTranslated
8
AI & Machine Learningnvidia/skills

perf-moe-dispatcher-selection

Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.

🇺🇸|EnglishTranslated
8
AI & Machine Learningnvidia/skills

nemo-gym-pivot-datasets

Use when creating, validating, or documenting Nemo Gym pivot datasets from rollout, trajectory, chat-completion, Responses API, or tool-call artifacts. Covers Gym Responses-style row conversion, pivot selection, single-step tool-use configs, agent_ref alignment, verifier knobs, expected-action row contracts, and train/eval usage.

🇺🇸|EnglishTranslated
8
5 scripts/Checked
AI & Machine Learningnvidia/skills

dali-dynamic-mode

Use when writing DALI data loading or preprocessing code with `nvidia.dali.experimental.dynamic` (ndd), or when converting DALI pipeline-mode code to dynamic mode, or when the user asks about DALI dynamic mode, imperative DALI, or ndd. Use this skill any time someone mentions 'ndd', 'dynamic mode', or wants to load/augment data with DALI outside of a pipeline definition.

🇺🇸|EnglishTranslated
8
1 scripts/Checked
AI & Machine Learningnvidia/skills

perf-memory-tuning

Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes.

🇺🇸|EnglishTranslated
8
AI & Machine Learningnvidia/skills

run-on-slurm

How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.

🇺🇸|EnglishTranslated
8
AI & Machine Learningnvidia/skills

deployment

Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM. Use when user says "deploy model", "serve model", "start vLLM server", "launch SGLang", "TRT-LLM deploy", "AutoDeploy", "benchmark throughput", "serve checkpoint", or needs an inference endpoint from a HuggingFace or ModelOpt-quantized checkpoint. Do NOT use for quantizing models (use ptq) or evaluating accuracy (use evaluation).

🇺🇸|EnglishTranslated
8
1 scripts/Attention
AI & Machine Learningnvidia/skills

deepstream-dev

NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.

🇺🇸|EnglishTranslated
8
AI & Machine Learningafumu/openteam

openteam-control

Used when an Agent needs to control OpenTeam via the local openteamcli: create AI group chats, add temporary roles, publish tasks, wait for replies, read results, or continue existing group chats.

🇨🇳|ChineseTranslated
8
1...494495496497498...708
Page