Skip to main content
تشغيل أي مهارة في Manus
بنقرة واحدة
مستودع GitHub

vllm-skills

يحتوي vllm-skills على 6 من skills المجمعة من vllm-project، مع تغطية مهنية على مستوى المستودع وصفحات skill داخل الموقع.

skills مجمعة
6
Stars
87
محدث
2026-04-03
Forks
23
التغطية المهنية
3 فئات مهنية · 100% مصنفة
مستكشف المستودعات

Skills في هذا المستودع

vllm-bench-random-synthetic
علماء البيانات

Run vLLM performance benchmark using synthetic random data to measure throughput, TTFT (Time to First Token), TPOT (Time per Output Token), and other key performance metrics. Use when the user wants to quickly test vLLM serving performance without downloading external datasets.

2026-04-03
vllm-bench-serve
علماء البيانات

Benchmark vLLM or OpenAI-compatible serving endpoints using vllm bench serve. Supports multiple datasets (random, sharegpt, sonnet, HF), backends (openai, openai-chat, vllm-pooling, embeddings), throughput/latency testing with request-rate control, and result saving. Use when benchmarking LLM serving performance, measuring TTFT/TPOT, or load testing inference APIs.

2026-04-03
vllm-deploy-docker
مديرو الشبكات وأنظمة الحاسوب

Deploy vLLM using Docker (pre-built images or build-from-source) with NVIDIA GPU support and run the OpenAI-compatible server.

2026-04-03
vllm-deploy-k8s
مديرو الشبكات وأنظمة الحاسوب

Deploy vLLM to Kubernetes (K8s) with GPU support, health probes, and OpenAI-compatible API endpoint. Use this skill whenever the user wants to deploy, run, or serve vLLM on a Kubernetes cluster, including creating deployments, services, checking existing deployments, or managing vLLM on K8s.

2026-04-03
vllm-deploy-simple
مطوّرو البرمجيات

Quick install and deploy vLLM, start serving with a simple LLM, and test OpenAI API.

2026-04-03
vllm-prefix-cache-bench
مطوّرو البرمجيات

This is a skill for benchmarking the efficiency of automatic prefix caching in vLLM using fixed prompts, real-world datasets, or synthetic prefix/suffix patterns. Use when the user asks to benchmark prefix caching hit rate, caching efficiency, or repeated-prompt performance in vLLM.

2026-04-03