Loading...
Loading...
Found 402 Skills
Benchmark a model served on MAX with the `max benchmark` command: measure throughput (tokens/sec), latency (TTFT, TPOT, inter-token latency), and GPU utilization by driving load against a running `max serve` endpoint. Use this whenever the user wants to benchmark, load-test, or measure the performance of a MAX model, get tokens-per-second / TTFT / TPOT numbers, run a concurrency or request-rate sweep, compare latency vs throughput, size a deployment, or produce benchmark JSON, even if they don't say "benchmark" by name. Also use when a `max benchmark` run fails to connect or reports zero/garbage numbers.
Early-access skill for Mimiry's softlaunch GPU compute platform. Use this skill whenever the user wants to run a GPU job, start a compute session, train a model, launch a container on a GPU, check their balance, manage running sessions, or build a compute job script on the Mimiry softlaunch environment. Also triggers when the user mentions Mimiry softlaunch, Mimiry compute, GPU sessions, SSH-ing into a session, or asks to "run this on a GPU" or "launch a training job". Covers both quick one-liners and interactive job-building workflows. This is the softlaunch (early beta) version — the API and features may change.
Runpod CLI to manage your GPU workloads.
runpod-flash — code-first serverless: write Python locally, run it on remote Runpod GPUs/CPUs with `flash dev` (hot-reload + live worker logs), then `flash deploy`. Use for @Endpoint/@remote functions, resource config, and debugging flash deployments. For CLI-only infra management use runpodctl or runpod-mcp.
DigitalOcean Gradient AI agentic cloud and AI platform for building, training, and deploying AI agents on GPU infrastructure with foundation models, knowledge bases, and agent routes. Use when planning or operating AI agents on DigitalOcean.
Use when working with ANY GPU rendering, Metal, OpenGL migration, shaders, 3D content, RealityKit, AR, or display performance. Covers Metal migration, shader conversion, RealityKit ECS, RealityView, variable refresh rate, ProMotion.
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
Use when launching cloud VMs, Kubernetes pods, or Slurm jobs for GPU/TPU/CPU workloads, training or fine-tuning models on cloud GPUs, deploying inference servers (vllm, TGI, etc.) with autoscaling, writing or debugging SkyPilot task YAML files, using spot/preemptible instances for cost savings, comparing GPU prices across clouds, managing compute across 25+ clouds, Kubernetes, Slurm, and on-prem clusters with failover between them, troubleshooting resource availability or SkyPilot errors, or optimizing cost and GPU availability.
Expert knowledge for GPU shader development across GLSL, HLSL, ShaderLab, and compute shadersUse when "write shader, shader code, GLSL, HLSL, ShaderLab, vertex shader, fragment shader, pixel shader, compute shader, post-processing, visual effects, screen effect, bloom effect, outline shader, toon shader, water shader, dissolve effect, custom material, render texture, GPU compute, raymarching, SDF, signed distance field, shader, glsl, hlsl, shaderlab, gpu, graphics, rendering, visual-effects, post-processing, compute, webgl, vulkan, directx, metal, opengl" mentioned.
Deploys ML and LLM models on TrueFoundry with GPU inference servers (vLLM, TGI, NVIDIA NIM). Uses YAML manifests with `tfy apply`. Use when serving language models, deploying Hugging Face models, or hosting GPU-accelerated inference endpoints.
On-demand and reserved GPU clusters (H100, H200, B200) on Together AI with Kubernetes or Slurm orchestration, shared storage, credential management, and cluster scaling for ML and HPC jobs. Reach for it when the user needs multi-node compute or infrastructure control rather than a managed model endpoint.