[workspace]

[package]
name = "pipeline-parallel-inference"
version = "0.1.0"
edition = "2024"
publish = false

[dependencies]
swactor = { path = "../..", features = ["transport", "serde", "std"] }
swactor-process = { path = "../../crates/process" }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
reqwest = { version = "0.12", features = ["json", "stream"] }
futures-util = "0.3"
tokio = { version = "1", features = ["full"] }
distribution = { path = "../../crates/distribution", features = ["iroh"] }
# Live runtime dashboard (HTTP overview/actors/topology pages + the
# datastream-fed Fleet tab, served on localhost when PP_DASHBOARD is set).
dashboard = { path = "../../crates/dashboard" }
iroh = "0.98"
urlencoding = "2"
base64 = "0.22"
libc = "0.2"

[[bin]]
name = "pp-worker"
path = "src/bin/pp_worker.rs"

[[bin]]
name = "pp-orchestrator"
path = "src/bin/pp_orchestrator.rs"

[dev-dependencies]
wiremock = "0.6"
tracing-subscriber = { version = "0.3", features = ["env-filter"] }

# These binaries are shipped to rented GPU nodes over the docker image on a
# cold lease, and over scp through vast.ai's throttled SSH proxy for manual
# swaps. Stripping debug symbols (~26MB -> ~18MB) trims both at no runtime cost.
[profile.release]
strip = true