[package]
name = "mesh-engine-gguf"
version.workspace = true
edition.workspace = true
license.workspace = true
repository.workspace = true
description = "Mesh — a real serving backend: wraps the family's pure-Rust GGUF/Metal inference substrate as a ServingEngine, so the mesh routes and meters actual model tokens. Behind the `gguf` feature so the default workspace build stays light."

[dependencies]
mesh-schema = { workspace = true }
mesh-engine = { workspace = true }
jouleclaw-loader-gguf = { workspace = true, optional = true }
thiserror = { workspace = true }
# Used only by the `serve_falcon` bin (required-features = ["gguf"]).
mesh-core = { workspace = true, optional = true }
mesh-meter = { workspace = true, optional = true }
mesh-router = { workspace = true, optional = true }
jcp-schema = { workspace = true, optional = true }
jcp-grant = { workspace = true, optional = true }
ed25519-dalek = { workspace = true, optional = true }
serde_json = { workspace = true, optional = true }
mesh-openai = { path = "../mesh-openai", optional = true }
# The GPU load for `ProcessMeter`'s liveness probe, with the `metal` feature.
jouleclaw-backend-apple = { workspace = true, optional = true }

[features]
default = []
# Pull the GGUF/safetensors loader and compile the real engines. Off by default:
# the loader is a heavier dependency (mmap, tokenizer, per-arch decode), and the
# default `cargo test --workspace` should not need model weights on disk.
gguf = [
    "dep:jouleclaw-loader-gguf",
    "dep:mesh-core",
    "dep:mesh-meter",
    "dep:mesh-router",
    "dep:jcp-schema",
    "dep:jcp-grant",
    "dep:ed25519-dalek",
    "dep:serde_json",
    "dep:mesh-openai",
    "mesh-openai/server",
]
# Apple Silicon UMA Metal overlay (zero-copy GGUF → GPU). Forwarded to the loader.
# Decode on the GPU, in process, and meter each serve by this process's own CPU
# and GPU energy (`mesh_meter::ProcessMeter`) rather than the load estimator.
metal = ["gguf", "jouleclaw-loader-gguf/metal", "mesh-meter/hw-meter-apple", "dep:jouleclaw-backend-apple"]
# Data-parallel matmul in the loader (faster CPU decode).
rayon = ["gguf", "jouleclaw-loader-gguf/rayon"]

[[bin]]
name = "serve_falcon"
path = "src/bin/serve_falcon.rs"
required-features = ["gguf"]

[[bin]]
name = "serve_openai_falcon"
path = "src/bin/serve_openai_falcon.rs"
required-features = ["gguf"]

[[bin]]
name = "serve_gemma_metered"
path = "src/bin/serve_gemma_metered.rs"
required-features = ["metal"]

[lints]
workspace = true