← Latest products

Smile-Serve

Inference Server for ML, ONNX, and LLM. Statistical Machine Intelligence & Learning Engine. SMILE Serve is a production-ready inference server built on [Quarkus]( https://quarkus.io/ ) that brings together three complementary inference capabilities on the JVM: - **Classic ML**: `/api/v1/models` for serialized SMILE models (`.sml`) - **ONNX Runtime**: `/api/v1/onnx` for any model in the ONN.

Open source

6,429 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Spinf-serve

    github.com

    inference server for bulk scoring and decisions

    Hacker News22 pts

  2. Willow Inference Server

    github.com

    Optimized ASR/TTS/LLM for Willow/WebRTC/REST

    Hacker News13 pts

  3. 50+ LLMs on 2 GPUs with 2-Second Swapping? We built AI-Native Runtime

    github.com

    InferX: Inference as a Service Platform

    Hacker News5 pts

  4. FlashQwen

    github.com

    A from-scratch CUDA inference engine for Qwen3

    Hacker News5 pts

  5. Gooey

    github.com

    Opinionated Go WebASM Framework

    Hacker News5 pts