Karti Tripathi
a4490ec80e
ci / rust (push) Successful in 2m26s
Governed compute for unified-memory AI hardware — machines where CPU and GPU share one pool and there is no separate VRAM allocation to bounce off. Over-commit that pool and the box thrashes and wedges, SSH and ping included, before the OOM killer gets a turn. Compute does not run inference. It supervises the servers that do: admission control against both a declared budget and what the machine actually has free, a 1 Hz watchdog that stops the newest model before thrash, Scenes activated as one transactional unit with rollback, process ownership bound to (boot_id, pid, start_time_ticks, pgid) so a reused PID can never be group-killed, a protocol-transparent gateway, an MCP server, and a read-only HTTP API for dashboards. Registry footprints in this release are measured on a live node rather than estimated. One binary, six direct dependencies. Apache-2.0. Generated by scripts/publish-compute.sh, which refuses to publish a tree it cannot prove clean.
623 B
623 B
Contributing to Lumbridge Compute
Contributions are welcome. Changes land as small, reviewable commits.
Development
cargo test
cargo fmt --check
cargo clippy --all-targets
cargo build --release
Changes to the lumbridge/v1 scene or eval contracts require fixtures, backward-
compatibility notes, and documentation. Never add secrets, private model tokens,
personal voice samples, internal hostnames, or arbitrary commands to shareable
scene/eval manifests.
Performance changes should include before/after JSON artifacts and the complete hardware/model/runtime configuration needed to reproduce them.