aria-engine runtime and FFI

aria-engine runs Aria model bundles (weight.bin + config.json) locally for language, vision, and VLA/policy inference. Ship it as a standalone binary or embed the FFI shared library into your application.

Install

Fetch the latest release for your platform from the downloads page or programmatically:

curl -s https://ariacompute.com/api/download/engine-latest \
  | jq -r '.assets[] | select(.name | test("linux-x86_64.tar.gz$")) | .url' \
  | xargs curl -L -o aria-engine.tar.gz
tar xf aria-engine.tar.gz

On the China site the same endpoint mirrors from Gitee. Use https://ariacompute.cn/api/download/engine-latest.

Get a model bundle

Download a bundle with your API key, then unpack it:

curl -L -H "Authorization: Bearer bfvk-XXXXXXXXXXXXXXXX" \
  "https://ariacompute.com/api/models/gemma-4-e2b-it/download?quant=int4&sdk=v1.0" \
  -o gemma-4-e2b-it_q4.zip
unzip gemma-4-e2b-it_q4.zip -d ./models/gemma-4-e2b-it_q4

The bundle contains weight.bin, config.json, and optional tokenizer sidecars. See Models for the full layout and quantization matrix.

Run inference from the CLI

./aria-engine serve \
  --model ./models/gemma-4-e2b-it_q4 \
  --host 127.0.0.1 --port 8080

The server exposes an OpenAI-compatible /v1/chat/completions endpoint on the configured port. Point any OpenAI-compatible client at http://127.0.0.1:8080/v1.

Embed with libaria-engine_ffi

Each release ships a shared library alongside the CLI: libaria-engine_ffi-linux-x86_64.so, libaria_engine_ffi.dylib, aria_engine_ffi.dll. Link it from C, Rust, Python (via ctypes/cffi), Swift, or any language with a C ABI.

C
Python

app.c

#include "aria_engine.h"

int main(void) {
    AriaEngine *engine = aria_engine_new("./models/gemma-4-e2b-it_q4");
    char *out = aria_engine_generate(engine, "Hello, world.", 256);
    printf("%s\n", out);
    aria_engine_free_string(out);
    aria_engine_free(engine);
    return 0;
}

import ctypes
lib = ctypes.CDLL("./libaria-engine_ffi-linux-x86_64.so")
lib.aria_engine_new.restype = ctypes.c_void_p
lib.aria_engine_generate.restype = ctypes.c_char_p
engine = lib.aria_engine_new(b"./models/gemma-4-e2b-it_q4")
out = lib.aria_engine_generate(engine, b"Hello, world.", 256)
print(out.decode())

Bundled C headers ship in the release archive under include/. Consult them for the full FFI surface: streaming callbacks, KV cache management, tokenizer helpers, and cleanup functions.

Model fetch inside the engine

The aria-engine CLI can also fetch models directly from Hugging Face (international) or ModelScope (China). This is separate from the Dashboard model registry and does not consume your Aria Compute wallet:

./aria-engine pull ariacompute/gemma-4-e2b-it_q4

Get Started

Core Concepts

Guides

SDKs

Resources

aria-engine runtime and FFI

Install

Get a model bundle

Run inference from the CLI

Embed with libaria-engine_ffi

Model fetch inside the engine

​Install

​Get a model bundle

​Run inference from the CLI

​Embed with libaria-engine_ffi

​Model fetch inside the engine

Install

Get a model bundle

Run inference from the CLI

Embed with libaria-engine_ffi

Model fetch inside the engine