intel/skills

intel/skills · skills/ai-inference-deploy/SKILL.md · Top-level router for an Intel GPU inference request that has not settled what it wants yet. Use for the bare ask —…

intel/skills · skills/cuda-to-xpu-migration/SKILL.md · Create a CUDA-to-XPU migration assessment for an existing AI repo. Identify CUDA-specific assumptions, route to the…

intel/skills · skills/dpnp-interop/SKILL.md · Passing dpnp arrays to and from other Python libraries on Intel CPUs and GPUs. Use when dpnp numeric work has to feed…

intel/skills · skills/dpnp-io/SKILL.md · Reading and writing files from dpnp code on Intel CPUs and GPUs. Use when the user needs to load an array into dpnp or…

intel/skills · skills/dpnp-linalg-fft/SKILL.md · Linear algebra and FFT with dpnp on Intel CPUs and GPUs, backed by oneMKL. Use when a matrix multiply, solve…

intel/skills · skills/dpnp-memory/SKILL.md · Device memory management for dpnp arrays on Intel CPUs and GPUs. Use when a dpnp script grows in memory until it fails…

intel/skills · skills/dpnp-migration/SKILL.md · Porting an existing NumPy or CuPy program to dpnp on Intel CPUs and GPUs. Use when deciding whether a codebase can run…

intel/skills · skills/dpnp-quickstart/SKILL.md · NumPy-compatible array operations optimized for Intel hardware. Use when the user wants to migrate or port NumPy code…

intel/skills · skills/dpnp-random/SKILL.md · Random number generation with dpnp on Intel CPUs and GPUs, backed by oneMKL. Use when NumPy random calls move to dpnp…

intel/skills · skills/dpnp-troubleshooting/SKILL.md · Diagnosing dpnp failures on Intel CPUs and GPUs. Use when dpnp raises NotImplementedError or an unexpected TypeError…

intel/skills · skills/linux-perf/SKILL.md · Profile and fix Linux performance problems using `perf`. Workflows: (A) hardware counters -- IPC, cache-miss, branch…

intel/skills · skills/llamacpp-xpu-run/SKILL.md · Run a GGUF model on an Intel GPU using llama.cpp's SYCL backend (Level Zero) with the official intel.Dockerfile. Covers…

intel/skills · skills/mkl-extension-advisor/SKILL.md · Deciding whether Intel's MKL extension packages apply to NumPy or SciPy code on Intel CPUs. Use when a user asks…

intel/skills · skills/model-can-it-fit/SKILL.md · Estimate whether a Hugging Face decoder-only LLM, MoE, or VLM fits in Intel GPU VRAM for a quantization, context…

intel/skills · skills/model-config-recommend/SKILL.md · Recommend how to configure vLLM-XPU for a Hugging Face decoder-only LLM on Intel Arc B-series GPUs: choose…

intel/skills · skills/onetbb-quickstart/SKILL.md · Getting started with Intel oneTBB for C++ parallelism on Intel CPUs. Use when a C++ loop or reduction should run on…

intel/skills · skills/openvino-gpu-run/SKILL.md · Serve an LLM on an Intel GPU with OpenVINO Model Server (OVMS) behind an OpenAI-compatible API — /v1/chat/completions…

intel/skills · skills/performance-patterns/SKILL.md · Detect and fix x86/C/C++ performance patterns from source code or profiling output (perf, VTune, flamegraphs). Invoke…

intel/skills · skills/phoronix-test-suite/SKILL.md · Install, run, parse, and optimize benchmarks from the Phoronix Test Suite (PTS). Use this skill whenever the user…

intel/skills · skills/sglang-xpu-bench/SKILL.md · Benchmark a **running SGLang-XPU server** on an Intel GPU using `sglang.bench_serving`. Measures TTFT, TPOT, ITL…

intel/skills · skills/sglang-xpu-run/SKILL.md · Serve a Hugging Face safetensors model on an Intel GPU using SGLang's XPU backend with the OpenAI-compatible API…

intel/skills · skills/torch-xpu-bench/SKILL.md · Benchmark a Hugging Face model on an Intel GPU through pure PyTorch + Transformers, **single-process, no HTTP server**…

intel/skills · skills/torch-xpu-profile/SKILL.md · Profile a Hugging Face model on Intel GPU at the **PyTorch level** with `torch.profiler` and Kineto. Captures CPU + XPU…

intel/skills · skills/torch-xpu-run/SKILL.md · Run an arbitrary Hugging Face safetensors model on an Intel GPU using **upstream PyTorch** (>= 2.8) with the built-in…

intel/skills · skills/vllm-xpu-bench/SKILL.md · Benchmark a **running vLLM-XPU OpenAI-compatible server** on an Intel GPU using `vllm bench`. Measures TTFT…

intel/skills · skills/vllm-xpu-profile/SKILL.md · Profile a running vLLM-XPU server with torch.profiler around a window of real requests, either via /start_profile and…

intel/skills · skills/vllm-xpu-run/SKILL.md · Serve a Hugging Face safetensors model on an Intel GPU with upstream vLLM-XPU's OpenAI-compatible API, or check whether…

intel/skills · skills/xpu-container-run/SKILL.md · Launch a Docker container with Intel GPU access on Linux. Encodes the correct combination of `--device /dev/dri`…

intel/skills · skills/xpu-deploy-plan/SKILL.md · Plan an end-to-end Intel XPU model deployment by chaining existing skills. Calls xpu-runtime-preflight (readiness)…

intel/skills · skills/xpu-discover/SKILL.md · Inventory Intel GPUs (Arc, Arc Pro) on a Linux host. Detect devices, collect driver, firmware and component-health…

intel/skills · skills/xpu-model-type-detect/SKILL.md · Before loading a Hugging Face model on Intel XPU, detect its actual type (text generation, text encoder, seq2seq…

intel/skills · skills/xpu-port/SKILL.md · Execute a single-target CUDA-to-XPU port of a PyTorch repo with libcst-based scan, mechanical rewrite, and CPU FP64 vs…

intel/skills · skills/xpu-profile-unitrace/SKILL.md · Profile Intel-XPU workloads at the SYCL / Level Zero kernel level via Intel pti-gpu's unitrace. Captures per-API-call…

intel/skills · skills/xpu-runtime-preflight/SKILL.md · Run a read-only go/no-go preflight before any Intel GPU/XPU skillpack work. Checks the GPU driver binding, /dev/dri…

intel/skills · skills/xpu-system-setup/SKILL.md · First-time setup for Intel XPU/GPU hosts. Installs the Intel OMIX (Open Middleware Xe) stack — Level Zero, OpenCL, SYCL…