AI Agent Skills

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-c…

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

Benchmarks LLM inference and drives GPU kernel optimization with Magpie. Use when the user wants to benchmark vLLM, SGLang, or Atom; capture torch traces; post-process i…

Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the Hyperloom multi-agent optimizer. Given a

A tiny single-file coding agent for self-hosted models (llama.cpp / vLLM / SGLang).

Autoscale LLM (vLLM, SGLang, LMDeploy) inferences on Kubernetes (and others)

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inferen…

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 whe…

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` p…