gpu-ai-skills

In the author's own words, from each skill's SKILL.md.

• cuda-to-xpu-migration

  Create a CUDA-to-XPU migration assessment for an existing AI repo. Identify CUDA-specific assumptions, route to the right XPU skills, produce a migration report. Use when the user has a CUDA repo, notebook, Dockerfile, launch script, HF / vLLM / SGLang workload, or Triton kernel and asks to migrate it to Intel Arc / Arc Pro / Battlemage / XPU — including "convert this to XPU" / "move it to XPU" a…

  plugins/intel-gpu-ai-skills/skills/cuda-to-xpu-migration/SKILL.md on GitHub (opens in a new tab)

• enable-xpu-monitoring

  Deploy a Prometheus + Grafana + XPU Manager monitoring stack on an Intel GPU host using the intel/xe-full-stack-monitoring repo (plain Docker Compose). Brings up containers for real-time GPU, CPU, and vLLM metrics collection and visualization. Use when the user wants to monitor XPU utilization, temperature, power, memory, or vLLM inference performance.

  plugins/intel-gpu-ai-skills/skills/enable-xpu-monitoring/SKILL.md on GitHub (opens in a new tab)

• llamacpp-xpu-run

  Run a GGUF model on an Intel GPU using llama.cpp's SYCL backend (Level Zero) with the official intel.Dockerfile. Covers building the Docker image from source at a pinned tag, launching llama-server with an OpenAI-compatible API, device selection, multi-GPU layer splitting, all recommended runtime env vars, flash-attention, and quantisation selection. Use when the user has a GGUF model and wants f…

  plugins/intel-gpu-ai-skills/skills/llamacpp-xpu-run/SKILL.md on GitHub (opens in a new tab)

• model-can-it-fit

  Estimate whether a Hugging Face decoder-only LLM, MoE, VLM, sliding-window, or hybrid state-space (SSM) model fits in Intel GPU VRAM for a quantization, context length, concurrency, runtime, and tensor-parallel setting. Use for memory-fit or max-model-len planning before launch. Reports weights, KV cache, recurrent state, activations, framework overhead, and first mitigation. Not for diffusion. M…

  plugins/intel-gpu-ai-skills/skills/model-can-it-fit/SKILL.md on GitHub (opens in a new tab)

• model-config-recommend

  Recommend how to configure vLLM-XPU for a Hugging Face decoder-only LLM on Intel Arc B-series GPUs: choose quantization, KV dtype, DP/TP layout, max concurrency, and max context using roofline math against published hardware specs. Use when the user asks "How should I configure vLLM?", requests the best vLLM configuration, or asks how to use one or multiple Arc cards. Must run recommend.py; predi…

  plugins/intel-gpu-ai-skills/skills/model-config-recommend/SKILL.md on GitHub (opens in a new tab)

• sglang-xpu-bench

  Benchmark a **running SGLang-XPU server** on an Intel GPU using `sglang.bench_serving`. Measures TTFT, TPOT, ITL, end-to-end latency, and throughput against the OpenAI-compatible endpoint. Use after sglang-xpu-run. Not for vLLM servers (use vllm-xpu-bench) or no-server PyTorch (use torch-xpu-bench).

  plugins/intel-gpu-ai-skills/skills/sglang-xpu-bench/SKILL.md on GitHub (opens in a new tab)

• sglang-xpu-run

  Serve a Hugging Face safetensors model on an Intel GPU using SGLang's XPU backend with the OpenAI-compatible API. Pins the validated `lmsysorg/sglang:v<version>-xpu` release image and flags newer unvalidated releases, then covers the container flag set for Intel DRM devices, the UMD/kernel pairing the image pins, the `--device xpu --attention-backend intel_xpu` flag set, page-size and quantizatio…

  plugins/intel-gpu-ai-skills/skills/sglang-xpu-run/SKILL.md on GitHub (opens in a new tab)

• torch-xpu-bench

  Benchmark a Hugging Face model on an Intel GPU through pure PyTorch + Transformers, **single-process, no HTTP server**. Measures generate() throughput in tokens/sec, time-to-first-token, decode-step latency, and peak XPU memory. Also covers diffusion and encoder-only models via `references/non-llm-snippets.md`. Use after **model-can-it-fit** to validate predicted memory against `torch.xpu.max_mem…

  plugins/intel-gpu-ai-skills/skills/torch-xpu-bench/SKILL.md on GitHub (opens in a new tab)

• torch-xpu-profile

  Profile a Hugging Face model on Intel GPU at the **PyTorch level** with `torch.profiler` and Kineto. Captures CPU + XPU timeline, exports Chrome trace, identifies hottest kernels and async-overlap gaps. Use when the user asks why a model is slow, which op is the bottleneck, or where the GPU is idle. Not for profiling inside a running vLLM server (use vllm-xpu-profile) or for SYCL-kernel-level sig…

  plugins/intel-gpu-ai-skills/skills/torch-xpu-profile/SKILL.md on GitHub (opens in a new tab)

• torch-xpu-run

  Run an arbitrary Hugging Face safetensors model on an Intel GPU using **upstream PyTorch** (>= 2.8) with the built-in `torch.xpu` device. Covers loading from the Hub, picking the right dtype, autocast, multi-GPU with accelerate's `device_map`, and the CUDA -> XPU code translation a user has to do once. Use for the Transformers / Accelerate / Diffusers path. Not for OpenAI-compatible serving (use…

  plugins/intel-gpu-ai-skills/skills/torch-xpu-run/SKILL.md on GitHub (opens in a new tab)

• vllm-omni-xpu-run

  Bring up a vLLM-Omni server (`vllm serve --omni`) on Intel Arc / Arc Pro B-series GPUs (XPU) for omni-modality and generative models — Qwen2.5-Omni / Qwen3-Omni chat, text-to-image (Qwen-Image, Z-Image, FLUX), video (Wan) and TTS (Qwen3-TTS). Covers building the image from upstream `docker/Dockerfile.xpu` on the matching `vllm/vllm-openai-xpu` base (no prebuilt XPU image or wheel exists), contain…

  plugins/intel-gpu-ai-skills/skills/vllm-omni-xpu-run/SKILL.md on GitHub (opens in a new tab)

• vllm-xpu-bench

  Benchmark a **running vLLM-XPU OpenAI-compatible server** on an Intel GPU using `vllm bench`. Measures TTFT (time-to-first-token), TPOT (time-per-output-token), ITL (inter-token latency), end-to-end latency, and throughput under concurrency. Covers online (`vllm bench serve`) and offline (`vllm bench throughput`) modes; concurrency sweeps and quant comparison live in `references/sweep-and-compare…

  plugins/intel-gpu-ai-skills/skills/vllm-xpu-bench/SKILL.md on GitHub (opens in a new tab)

• vllm-xpu-profile

  Profile a running vLLM-XPU server with torch.profiler around a window of real requests, either via /start_profile and /stop_profile HTTP endpoints or via vllm bench --profile for offline runs. Use to find the dominant op under real concurrent traffic. Not for pure PyTorch (use torch-xpu-profile), SYCL kernel-level signal (use xpu-profile-unitrace), throughput numbers (use vllm-xpu-bench), or non-…

  plugins/intel-gpu-ai-skills/skills/vllm-xpu-profile/SKILL.md on GitHub (opens in a new tab)

• vllm-xpu-run

  Serve a Hugging Face safetensors model on an Intel GPU with upstream vLLM-XPU's OpenAI-compatible API, or check whether a model or architecture is currently documented on XPU. Covers live support lookup, image choice, container launch, known serve-flag requirements, model-impl fallback, and attention/quant compatibility. Use to launch /v1/chat/completions or /v1/completions, troubleshoot a launch…

  plugins/intel-gpu-ai-skills/skills/vllm-xpu-run/SKILL.md on GitHub (opens in a new tab)

• xpu-container-run

  Launch a Docker container with Intel GPU access on Linux. Encodes the correct combination of `--device /dev/dri`, render-group access, `--ipc=host`, `ZE_AFFINITY_MASK` pinning, Hugging Face cache mount, and `--entrypoint /bin/bash` for interactive use. Use when running any Intel-XPU container (vLLM-XPU, sglang-xpu, torch-XPU, llama.cpp SYCL, etc.) and the device must be visible inside. The CUDA a…

  plugins/intel-gpu-ai-skills/skills/xpu-container-run/SKILL.md on GitHub (opens in a new tab)

• xpu-deploy-plan

  Plan an end-to-end Intel XPU model deployment by chaining existing skills. Calls xpu-runtime-preflight (readiness), model-can-it-fit (sizing), model-config-recommend (flags), and the selected runtime skill (vllm-xpu-run / sglang-xpu-run / torch-xpu-run), then writes a single PLAN.md with one exact launch command, smoke test, and rollback to .out/skills/xpu-deploy-plan/. Use when the user asks for…

  plugins/intel-gpu-ai-skills/skills/xpu-deploy-plan/SKILL.md on GitHub (opens in a new tab)

• xpu-discover

  Inventory Intel GPUs (Arc, Arc Pro) on a Linux host. Detect devices, collect driver, firmware and component-health evidence, list processes using each XPU, and read live utilisation.

  plugins/intel-gpu-ai-skills/skills/xpu-discover/SKILL.md on GitHub (opens in a new tab)

• xpu-model-type-detect

  Before loading a Hugging Face model on Intel XPU, detect its actual type (text generation, text encoder, seq2seq, vision classification, vision-language, audio encoder, audio seq2seq, multimodal VL, diffusion, time-series, reward model, masked LM) so the agent picks the right `AutoModel` class and input kwargs. Prevents "got unexpected keyword argument 'pixel_values'" and "empty logits" errors fr…

  plugins/intel-gpu-ai-skills/skills/xpu-model-type-detect/SKILL.md on GitHub (opens in a new tab)

• xpu-port

  Execute a single-target CUDA-to-XPU port of a PyTorch repo with libcst-based scan, mechanical rewrite, and CPU FP64 vs target-dtype correctness verify on one forward pass. Use when the request says "port" — "port my repo to XPU", "port my repo at <path> to XPU", "rewrite the CUDA calls to XPU", "apply the mechanical transforms", "run the scan and rewrite", "make the port changes now". Not for the…

  plugins/intel-gpu-ai-skills/skills/xpu-port/SKILL.md on GitHub (opens in a new tab)

• xpu-profile-unitrace

  Profile Intel-XPU workloads at the SYCL / Level Zero kernel level via Intel pti-gpu's unitrace. Captures per-API-call and per-kernel timing, memory transfers, oneCCL / MPI events, and hardware counters PyTorch-level profilers cannot see. Use when a hot op is already known at the torch.profiler layer and the user needs the SYCL kernel beneath, or when profiling oneCCL collectives in multi-GPU runs…

  plugins/intel-gpu-ai-skills/skills/xpu-profile-unitrace/SKILL.md on GitHub (opens in a new tab)

• xpu-runtime-preflight

  Run a read-only go/no-go preflight before any Intel GPU/XPU skillpack work. Checks the GPU driver binding, /dev/dri permissions, render/video groups, Docker, /dev/shm, disk, proxy, and optional container-level XPU visibility; captures health and kernel-log evidence. Use when the user asks whether a machine is ready for XPU model work or needs a reusable lab readiness report. Not for launching wor…

  plugins/intel-gpu-ai-skills/skills/xpu-runtime-preflight/SKILL.md on GitHub (opens in a new tab)

• xpu-system-setup

  First-time setup for Intel XPU/GPU hosts. Installs the Intel OMIX (Open Middleware Xe) stack — Level Zero, OpenCL, SYCL compiler, oneMKL/oneDNN — plus clinfo, xpu-smi, user groups (render), and Docker, then runs a post-setup verification gate (including sycl-ls). Prompts before each installation by default (use --auto for unattended). Also handles Battlemage (Arc Pro B60/B70) kernel/runtime prere…

  plugins/intel-gpu-ai-skills/skills/xpu-system-setup/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 434k stars · 5 skills
• skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory. 315k stars · 30 skills
• superpowersby obra An agentic skills framework & software development methodology that works. 313k stars · 15 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 298k stars · 30 skills
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 230k stars · 1 skill
• skillsby anthropics Public repository for Agent Skills 188k stars · 19 skills