swactor/examples/pipeline-parallel-inference/Cargo.toml

45 lines
1.3 KiB
TOML
Raw Normal View History

[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"] }
tokio = { version = "1", features = ["full"] }
distribution = { path = "../../crates/distribution", features = ["iroh", "collector"] }
iroh = "0.98"
urlencoding = "2"
base64 = "0.22"
libc = "0.2"
# PROTOTYPE_BINARY_SWAP (spec §5.1): pp-gpu-node verifies an
# operator-supplied SHA-256 digest of the fetched replacement binary.
# Already a transitive dep of the iroh stack; pinned here as a direct
# dep so a future §5.1 removal can drop this line cleanly along with
# the swap module.
sha2 = "0.10"
[[bin]]
name = "pp-gpu-node"
path = "src/bin/pp_gpu_node.rs"
[[bin]]
name = "pp-smoke-run"
path = "src/bin/pp_smoke_run.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 on a redeploy.
# Stripping debug symbols (~26MB -> ~18MB) trims both paths at no runtime cost.
[profile.release]
strip = true