MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Use this skill when the operator is authoring, building, loading, or debugging a custom doca-bench plug-in — a versioned shared library with DOCA_EXPERIMENTAL-marked C entry points that doca-bench loa
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Read artifacts from the shared bench — the workspace where desks leave findings, verdicts, and work products for each other and the operator.
OfficialSkillMIT★ 40k in collectionNo key
Run `doca_bench` (DOCA 2.7.0 or newer) to measure throughput, bulk latency, precision latency, or maximum bandwidth for RDMA, Compress, AES-GCM, SHA, DMA, EC, Ethernet, Comch, or GPUNetIO on a host or
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Benchmark React or Next.js changes on Vercel Sandbox VMs with paired A/B statistics: react PR/commit vs base, or Next.js PR/commit vs base, measured end-to-end through the bench/render-pipeline app (r
OfficialSkillMIT★ 143k in collectionNo key
Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal. Use when selecting a starting recipe, compar
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
OfficialSkillApache-2.0★ 564 in collectionNo key
Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X"
OfficialSkillApache-2.0★ 11k in collectionNo key
Use when measuring Jetson Video Codec SDK or PyNvVideoCodec encode/decode throughput, comparing presets or surfaces, testing codec-worker capacity with authenticated samples and user media, or produci
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when a
OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key
Run the disk-backed DEFT AOI improvement loop for NVIDIA Cosmos Reason 3 / Cosmos3 models, using Nano by default and Edge or Super when explicitly requested: evaluate the base model on Proxy and froze
OfficialSkillApache-2.0 AND CC-BY-4.0★ 3.6k in collectionNo key
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT e
OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key
Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use recipe-runner/router-starter before this
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Write, append, or read desk journal entries. The journal is persistent memory — what survives session boundaries. A good entry has: what was done, current state, next step.
OfficialSkillMIT★ 40k in collectionNo key
Use this skill when the user is building, running, or interpreting the doca/tools/gpunetio_ib_write_bw client+server benchmark — a CUDA kernel on the client posts RDMA WRITE work requests through the
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Evidence-gated workflow for MoE performance optimization in Megatron Bridge. Covers measurement contracts, the Three Walls framework, parallel folding, profiling, matched A/B tuning, and final validat
OfficialSkillApache-2.0★ 3.6k in collectionNo key
This skill calculates key financial ratios and metrics from financial statement data for investment analysis
OfficialSkillMIT★ 53k in collectionNo key
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints
OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key
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/gpunet
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, Mean-Variance/SOCP variance caps, efficient frontiers, scenario generation, or NVIDIA cuOpt.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Who stands behind it
