Zachery Aaron Shores-Chmielewski
ae9ca3bcf3
Promote pipeline-parallel-inference to a first-class app and consolidate observability on the datastream wire, decoupling the dashboard crate from `distribution`. - apps/pipeline-parallel-inference: move the example out of `examples/` into `apps/` as its own workspace, rename binaries to `pp-worker`/`pp-orchestrator`, and strip release binaries - cluster: add `ClusterNode`, a synchronous facade over the actorized distribution protocol (IrohDriver + per-node Runtime hosting Swim/Registry/Metadata/Directory actors with a `MembershipFanout`), replacing ad-hoc `driver.node()`/`tick()` call sites - fleet: add per-node fleet telemetry that ships identity/resource records as `DatastreamFrame`s over the cluster transport to the orchestrator's `DatastreamSink`, folded into a `FleetView` on a 3s tick - provision: add best-effort, opt-in SSH boot-phase telemetry (`PP_DEPLOY_KEY`) that streams rented-node boot logs onto the orchestrator's datastream as `proc.boot.<stage>.*` - dashboard: rewire the crate dependency from `distribution` to `datastream`, drop the standalone `swactor-datastream-dashboard` binary, and rewrite `datastream_source.rs` to demux per-node frames into Overview/Distribution/Fleet views with live-node TTL filtering - distribution: refresh dist/netmap plugin copy and README from "Kademlia routing" to gossip-directory terminology Signed-off-by: Zachery Aaron Shores-Chmielewski <zacheryasc@gmail.com>
46 lines
1.5 KiB
TOML
46 lines
1.5 KiB
TOML
[workspace]
|
|
|
|
[package]
|
|
name = "pipeline-parallel-inference"
|
|
version = "0.1.0"
|
|
edition = "2024"
|
|
publish = false
|
|
|
|
[dependencies]
|
|
swactor = { path = "../..", features = ["transport", "serde", "std"] }
|
|
swactor-transport = { path = "../../crates/transport" }
|
|
# `ssh` enables the orchestrator's boot-phase telemetry: it SSHes into each
|
|
# rented node and streams the worker boot log onto its datastream.
|
|
swactor-process = { path = "../../crates/process", features = ["ssh"] }
|
|
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"] }
|
|
datastream = { path = "../../crates/datastream" }
|
|
# Live runtime dashboard (HTTP overview/actors/topology pages, 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
|