local-ai

vllm.cpp

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-aware scheduling, ...)
453 stars+5★ this week54 forksC++Updated 10/21/2026100% free · open source
What it does

vllm.cpp is a C++ engine that enables the creation of a community-oriented, 1:1, vLLM-alike model with continuous batching and paged KV storage, allowing for efficient and scalable AI model development

When to use it
  • •Building a custom AI model that requires continuous batching and paged KV storage
  • •Developing a community-driven AI project that needs a scalable and efficient engine
  • •Creating an AI application that requires a high degree of customization and control over the underlying model
Ready-to-paste prompt
./vllm --model example_model --prompt 'What is the meaning of life?'
Heads up: The project requires a C++ compiler (e.g. GCC) and CMake to be installed on the system, and the `config.toml` file needs to be properly configured before running the model
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/vllm-cpp && curl -fsSL https://workflowstacks.com/api/skills/vllm-cpp/claude-skill -o ~/.claude/skills/vllm-cpp/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

15
top-level files
19
folders
202.9M
source size
Apache-2.0
license
Key files
AGENTS.md
README.md
File tree
.agents/
.claude/
.githooks/
.github/
assets/
benchmarks/
cmake/
docker/
docs/
examples/
include/
release/
scripts/
src/
tests/
third_party/
tools/
triton_kernels/
website/
.clang-format
.dockerignore
.env.example
.gitattributes
.gitignore
Quick Actions
Details
Creator
mudler
Language
C++
Category
local-ai
Published
7/2/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/vllm-cpp.svg)](https://workflowstacks.com/skills/vllm-cpp?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.