MCPcopy
hub / github.com/ray-project/ray / start

Method start

python/ray/llm/tests/serve/mocks/mock_vllm_engine.py:52–54  ·  view source on GitHub ↗

Start the mock engine.

(self)

Source from the content-addressed store, hash-verified

50 self._is_paused = False
51
52 async def start(self):
53 """Start the mock engine."""
54 self.started = True
55
56 async def resolve_lora(self, lora_model: DiskMultiplexConfig):
57 """Resolve/load a LoRA model."""

Calls

no outgoing calls