AI & LLM Engineering · NVIDIA AI Platform · For developers

Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.

sgl-project/sglang

Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.

decolua/9router

Transcribes audio files into text or subtitles through 9Router's Whisper-compatible endpoint, using models from OpenAI, Groq, Gemini, Deepgram and others.

decolua/9router

Reviews recent code changes and checks if documentation needs updates.

NVlabs/alpasim

Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven.

dstackai/dstack

Guides moving Megatron Core GPTModel checkpoints, configs, training commands and launch scripts to HybridModel, following the repository's migration document.

NVIDIA/Megatron-LM

Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.

graphsignal/graphsignal

Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.

BBuf/AI-Infra-Auto-Driven-SKILLS

Drive a single-operator optimization campaign per .agents/guidance/OPTIMIZATIONGUIDELINES.md, with a deterministically enforced definition-of-done and versioned MR summary.

CVCUDA/CV-CUDA

Integrates a hosted API or local/open-weight model end-to-end across OpenTryOn (adapter, CLI registry, MCP, docs) and TryOn Studio (catalog, Connect keys, planner).

tryonlabs/opentryon

Install, convert, debug, and benchmark sim2real ONNX GPU and TensorRT inference backends on onboard JetPack 5 Orin hosts such as g1-cable.

EGalahad/sim2real

Builds a NeMo Gym (NVIDIA) variant of an RL environment. An agent skill from adithya-s-k/FineEnvs.

adithya-s-k/FineEnvs

This skill should be used when the user wants to set up, install, deploy, bootstrap, or "spin up" the Build-an-Agent workshop (a.k.a.

brevdev/workshop-build-an-agent

Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format.

dstackai/dstack

Prepare, validate, build, and use Nemotron Customizer airgap image bundles for offline clusters.

NVIDIA-NeMo/Nemotron

A skill your agent uses when quantizing a diffusion DiT with NVIDIA ModelOpt and making the resulting FP8 or NVFP4 checkpoint loadable, verifiable, and benchmarkable in SGLang Diffusion.

sgl-project/sglang

Write, debug, and optimize CUTLASS, CuTe, and CuTeDSL GPU kernels from local upstream source, examples, and headers.

slowlyC/agent-gpu-skills

Shows how to call NEAR AI Cloud through an OpenAI-compatible API and verify that inference ran in a TEE, using attestation checks and signed chat responses.

internet-court/internet-court-skill

Set up the NVIDIA "Build an Agent" DevX workshop as a working JupyterLab environment from INSIDE a locked-down OpenShell/NemoClaw sandbox, and hand the user the token URL + access commands.

brevdev/workshop-build-an-agent

基于 helpfile 工程经验，协助 agent 配置 CV 主机和边缘设备环境、编译视觉与推理依赖、接入摄像头视频并打包部署服务。适用于 Ubuntu、CentOS、Windows、macOS、Jetson、树莓派和 RK3399 的 CV 工程实施与故障排查，以及相关移动端配套工具；模型训练和纯算法设计不属于本技能主线。

LMIXR/CV_Deployment_skill

Port an FLA Triton kernel to Gluon when explicit layouts, asynchronous transfers, or scheduling can address a measured bottleneck.

fla-org/flash-linear-attention

Optimizes and serves LLMs on NVIDIA GPUs with TensorRT-LLM, covering quantization, in-flight batching, multi-GPU parallelism and the trtllm-serve command.

Orchestra-Research/AI-Research-SKILLs

Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch.

mydisha/keirouter

Serves AI models on AMD Instinct GPU hardware using vLLM. An agent skill from amd/skills.

amd/skills

dstack is an open-source control plane for GPU provisioning and orchestration across GPU clouds, Kubernetes, and on-prem clusters.

dstackai/dstack

GGUF format and llama.cpp quantization for efficient CPU/GPU inference.

Orchestra-Research/AI-Research-SKILLs

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware.

Orchestra-Research/AI-Research-SKILLs

A skill your agent uses when something is wrong: Search() hangs, all evaluations return INVALIDSCORE, scores aren't improving, every config returns the same number, ptxas errors fill the log, CV% is…

NVIDIA/CompileIQ

Write, debug, and optimize Triton and Gluon GPU kernels from local upstream tutorials, production kernels, language definitions, and compiler source.

slowlyC/agent-gpu-skills

Add a new CV-CUDA operator end-to-end per .agents/guidance/MAKEOPGUIDELINES.md, with a deterministically-enforced definition-of-done.

CVCUDA/CV-CUDA

Explains where HOT-Step generation time goes (LM/DiT/VAE), how the TensorRT paths activate, how to benchmark from logs, and which knobs trade quality for speed.

scragnog/HOT-Step-CPP

Estimate GPU memory usage for Megatron-based MoE (Mixture of Experts) and dense models.

yzlnew/infra-skills

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution.

Orchestra-Research/AI-Research-SKILLs

Covers serving LLMs with SGLang, whose RadixAttention reuses cached prefixes, and constraining output to JSON, regex or grammar for agent and tool-calling workloads.

Orchestra-Research/AI-Research-SKILLs

Sets up large-scale LLM training with NVIDIA Megatron-Core, choosing tensor, pipeline, data, context and expert parallelism for a given model size and GPU count.

Orchestra-Research/AI-Research-SKILLs

Generate vector embeddings via KeiRouter /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia embedding models for RAG, semantic search, similarity.

mydisha/keirouter

Run the Nemotron-3.5 Lightning Text2SQL LoRA fine-tuning tutorial (NeMo Megatron-Bridge) end-to-end for the user on a single node: data prep, checkpoint conversion, LoRA fine-tuning of the 30B-A3B…

NVIDIA-NeMo/Nemotron

Scaffold a new CV-CUDA operator — a complete, wired, building skeleton — and delegate the implementation to a human or another AI.

CVCUDA/CV-CUDA

Calculate training costs for Tinker fine-tuning jobs. An agent skill from sundial-org/skills.

sundial-org/skills

Run NVIDIA compute-sanitizer (memcheck, racecheck, initcheck, synccheck) against a Triton/TLX kernel to find runtime memory and synchronization bugs.

facebookexperimental/triton

Run, monitor, stop and report Primus convergence tests -- training a model on a real corpus and checking that the loss curve is healthy -- from a plain-language request such as "run convergence test…

AMD-AGI/Primus

Quick install and deploy vLLM, start serving with a simple LLM, and test OpenAI API.

vllm-project/vllm-skills

A skill your agent uses when deploying or operating standalone RTVI-CV-3D / MV3DT multi-camera 3D tracking for calibrated MP4/file inputs and live RTSP streams: missing-calibration handoff to AMC…

NVIDIA-AI-Blueprints/video-search-and-summarization

Uses Meta's LlamaGuard moderation model to screen prompts and model replies against six safety categories, with vLLM, FastAPI and NeMo Guardrails setups.

Orchestra-Research/AI-Research-SKILLs

Verify a new CV-CUDA operator against the deterministic final regression checklist (the /make-op done-gate).

CVCUDA/CV-CUDA

Collect and normalize environment facts (OS, Python, GPU, CUDA/ROCm, container state) before Quark installation or PTQ planning.

amd/Quark

A skill your agent uses when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed serving/model optimization task needs prior model-family PR evidence.

BBuf/AI-Infra-Auto-Driven-SKILLS

Upgrade focused runtime dependencies in AReaL. An agent skill from areal-project/AReaL.

areal-project/AReaL