Karti Tripathi
91a47fb42c
ci / rust (push) Successful in 2m26s
Governed compute for unified-memory AI hardware — the 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. A model starts only if committed + requested + margin fits the budget. The refusal is the feature. - A 1 Hz watchdog on MemAvailable that stops the newest model before thrash. - Scenes: named sets of models activated as one transactional unit, with pre-flight validation and rollback to the previously active Scene on failure. Scenes reference model ids, never weight paths or commands, so a Scene obtained from elsewhere cannot introduce code. - Process ownership bound to (boot_id, pid, start_time_ticks, pgid == pid), so a reused PID can never be group-killed. - A protocol-transparent TCP gateway, so clients keep one address while model runtimes move behind it. - An MCP server, so agents drive the node as tools rather than as a CLI. One binary, six direct dependencies, no async runtime outside the MCP surface. Published from the internal monorepo with a fresh history. The private development tree keeps its own history; nothing here carries it.
21 lines
297 B
Plaintext
21 lines
297 B
Plaintext
/target
|
|
.kuda/
|
|
eval-results/
|
|
**/*.rs.bk
|
|
Cargo.lock.orig
|
|
*.log
|
|
.DS_Store
|
|
|
|
# Secrets. docs/operations.md walks operators through generating keys, so these
|
|
# have to be unstageable by default rather than by discipline.
|
|
.env
|
|
.env.*
|
|
*.pem
|
|
*.key
|
|
*_rsa
|
|
*_ed25519
|
|
id_ed25519*
|
|
.ssh/
|
|
*secret*
|
|
*credentials*
|