[package]
name = "rtx-inference-stack"
version = "1.0.0"
edition.workspace = true
rust-version = "1.92"
authors = ["RustyTorch Team"]
license = "MIT OR Apache-2.0"
repository = "https://github.com/rustytorch/rustytorch"
description = "RTX high-performance inference stack - Production model serving"
keywords = ["machine-learning", "inference", "serving", "production", "deployment"]
categories = ["science", "web-programming::http-server"]

[dependencies]
# Core
rtx-tensor = { path = "../../core/rtx-tensor", version = "1.0.0" }
rtx-runtime = { path = "../../core/rtx-runtime", version = "1.0.0" }

# Inference
rtx-inference = { path = "../../production/rtx-inference", version = "1.0.0" }
rtx-serving-api = { path = "../../production/rtx-serving-api", version = "1.0.0" }
rtx-streaming = { path = "../../production/rtx-streaming", version = "1.0.0" }
rtx-compress = { path = "../../training/rtx-compress", version = "1.0.0" }

[features]
default = []
# GPU inference via the engine's optional backends: candle + ONNX Runtime
# CUDA execution providers, plus CUDA tensor/runtime/compression support.
cuda = [
    "rtx-tensor/cuda",
    "rtx-runtime/cuda",
    "rtx-compress/cuda",
    "rtx-inference/candle-cuda",
    "rtx-inference/onnx-cuda",
]
metal = [
    "rtx-tensor/metal",
    "rtx-runtime/metal",
    "rtx-inference/candle-metal",
]

[dev-dependencies]
tokio-test = "0.4"
criterion = "0.5"
[lints]
workspace = true