Commit Graph
2 Commits
Author SHA1 Message Date
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
0ff373467c fix: correct vllm models-check test name and stripe cancel boolean (#270)
- vllm: rename test_empty_models_is_a_failure to
  test_models_check_parses_from_stub and fix its misleading docstring;
  it asserts positive-path parsing of the stub's served model list, not an
  empty-models failure.
- stripe: pass cancel_at_period_end as the boolean True instead of the
  string 'true', and normalize booleans to lowercase true/false during
  form encoding so the wire payload stays Stripe-compatible.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-03 20:37:46 -04:00
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
6181f1746d feat(skill): add vLLM inference-serving skill (#247) (#267)
* feat(skill): add vLLM inference-serving skill (#247)

Add a single-tool vllm skill covering Docker/Kubernetes deployment,
quantization-aware model configuration (tensor parallelism, KV cache),
the OpenAI-compatible API surface, throughput/latency benchmarking,
continuous batching tuning, GPU operation, and upgrade/rollback.

Ships a read-only vllm-health probe (stdlib-only, --json), fillable
serving-config and benchmark-run-record templates, seven dated
references with upstream sources, a human-facing README, tests, and a
schema-v1 eval manifest with six cases covering config, benchmarking,
and troubleshooting.

Route ml-engineering to the new skill via a resolvable link alongside
llama-cpp, add the vllm entry to the top-level README index, and
regenerate the tracked catalogs.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

* fix(skill): emit timeout exit 124 and bound /metrics reads in vllm-health

Address the review observations on the bundled probe: requests that exceed
--timeout now raise ProbeTimeout and make the tool exit 124 as documented
(previously they surfaced as exit 1), and the metrics check reads at most
64 KiB of /metrics and reports truncation instead of reading the whole body.
Adds tests for both behaviors.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

---------

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-03 19:31:36 -04:00