vllm-hust-clm-lifecycle

CLM: Context Lifecycle Management perception plugin for vLLM-HUST.

Consumes the scheduler-level request lifecycle events exposed by the host (RequestFinished / RequestPreempted, contract vllm.request-lifecycle.v1) and reports session-level KV growth to an out-of-tree CLM controller, which decides when to compact a long conversation.

Bundle ID: org.vllm-hust.clm-lifecycle (Extension Bundle v1, schema 1.0)

What it does

• Lifecycle-sink component (contract vllm.request-lifecycle.v1, execution plane scheduler): registers a sink on the engine's default-off typed EventBus. When a request finishes or is preempted, the sink attributes the KV footprint to a session (engine-side session_id, or a __default__ bucket) and reports growth to a controller endpoint.
• Default-off, zero-overhead when absent: the events only exist on hosts that carry the request-lifecycle hook; without them register() skips gracefully. Reports never block serving (failures are swallowed).

Install

pip install vllm-hust-clm-lifecycle

Enable

Requires a host that exposes vllm.v1.events (vllm-hust with the request-lifecycle hook). Enable via plugin loading:

# runtime registration (vllm.general_plugins)
export VLLM_PLUGINS=ascend,clm_lifecycle
# observation / static discovery (vllm.extension_bundles)
vllm-hust-ext extension inspect org.vllm-hust.clm-lifecycle

Environment

Parse failures on these variables fall back to defaults (empty values are tolerated).

Disable

unset VLLM_CLM_CONTROLLER VLLM_CLM_REPORT_BLOCKS VLLM_CLM_REPORT_INTERVAL
# or simply do not list clm_lifecycle in VLLM_PLUGINS
pip uninstall vllm-hust-clm-lifecycle

Development

pip install -e ".[test]"
python -m pytest tests/
ruff check .

tests/conftest.py stubs vllm.v1.events before the plugin is imported, so the test suite runs without a vLLM install.

License

Apache-2.0