0f9d756caa
Extend ml_training_service to dispatch GPU training jobs as K8s batch/v1 Jobs, collect results via a Rust sidecar uploader, and support model promotion with operator approval via fxt CLI. - K8s dispatcher creates Jobs on gpu-training pool with native sidecar - training_uploader crate: watches DONE/FAILED marker, uploads to S3, reports completion via ReportJobCompletion gRPC - PromotionManager compares metrics, queues better models for approval - 4 new proto RPCs: ReportJobCompletion, ListPendingPromotions, ApprovePromotion, RejectPromotion - fxt commands: train start, model list/approve/reject - Training binaries write DONE/FAILED markers + metrics.json - Dockerfile, K8s job template, and CI pipeline updated - StartTraining gracefully falls back to in-process when outside K8s - 27 new tests (16 service + 11 promotion), 141 total service tests pass Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
27 lines
698 B
TOML
27 lines
698 B
TOML
[package]
|
|
name = "training_uploader"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
rust-version.workspace = true
|
|
authors.workspace = true
|
|
license.workspace = true
|
|
description = "K8s sidecar: uploads training artifacts to S3 and reports completion via gRPC"
|
|
|
|
[dependencies]
|
|
tokio.workspace = true
|
|
anyhow.workspace = true
|
|
tracing.workspace = true
|
|
tracing-subscriber.workspace = true
|
|
serde.workspace = true
|
|
serde_json.workspace = true
|
|
clap.workspace = true
|
|
object_store = { workspace = true, features = ["aws"] }
|
|
bytes.workspace = true
|
|
tonic.workspace = true
|
|
tonic-prost.workspace = true
|
|
prost.workspace = true
|
|
|
|
[build-dependencies]
|
|
tonic-prost-build.workspace = true
|
|
prost-build.workspace = true
|