Loading...
Loading...
Found 20 Skills
Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, or another serving framework. Use when a user wants to find the best deployment command for one model across multiple serving frameworks under the same workload, GPU budget, and latency SLA.
Recipes and configs for serving LLMs locally on RTX 3090 GPUs using vLLM, llama.cpp, and SGLang with OpenAI-compatible API
Parse SGLang/vLLM startup logs to explain GPU memory use and request capacity. Use for KV cache budget, mem-fraction-static comparisons, OOM triage, and max-concurrency estimates.
Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.
Serves AI models on AMD Instinct GPU hardware using vLLM. Use this skill whenever the user wants to run, serve, deploy, start, host, or launch a language model on an AMD GPU, AMD Instinct, MI300X, MI325X, MI350X, or MI355X. Also use when the user mentions vLLM on ROCm, vLLM on AMD, serving on HBM, or asks how to get a model running on AMD data center hardware. Use when the user asks "run Qwen3", "serve DeepSeek", "start a vLLM endpoint", "get a model running on my AMD machine", or any similar phrasing. Handles the full flow: GPU detection, environment validation, vLLM configuration, launch, and health verification. Do not use for NVIDIA GPUs, consumer AMD GPUs (RX series, Radeon), Ryzen AI, NPU, MI250X, or MI100.
End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM serving performance by searching each framework's best deployment command, benchmarking them fairly, profiling SGLang if it is slower, identifying kernel/overlap/fusion bottlenecks, patching SGLang code, and revalidating with real model runs.
Serves an LLM on a supported AMD EPYC server CPU using vLLM with zentorch, in Docker, Podman, or conda. Use for "vLLM on CPU", "zentorch serving", or an EPYC CPU endpoint, including on a host that also has AMD Instinct GPUs. Detects the EPYC generation, validates the runtime, checks model support and RAM fit, sizes threads/KV/NUMA, confirms the plan, launches, and verifies the endpoint. Runs one instance on one socket and its memory. Reports and stops on failure; does not retry or debug. Use serving-llms-on-instinct when the endpoint should run on a GPU. Excludes multi-node, EPYC 4000, and pre-Zen4 EPYC without AVX-512.
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to self-hosted inference on GKE, or asks follow-up questions during such a migration (hardware sizing, model staging, manifest generation, validation, traffic cutover). DO NOT use for brand new GKE inference deployments with no existing workload to migrate (use gke-inference instead). DO NOT use if the user intends to automate the migration via the Gemini Cloud Assist MCP server.
Deploy and manage vLLM for high-throughput LLM inference. Configure continuous batching, tensor parallelism, quantization, and OpenAI-compatible API endpoints for production LLM serving.
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
Run an autonomous Humanize-governed vLLM SOTA performance loop for one LLM model: first perform the fixed fair vLLM/SGLang/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches vLLM code, optionally uses ncu-report-skill for kernel evidence, and revalidates until vLLM matches or beats the best observed framework under the same workload and SLA.