Setup the LLM asynchronously.
(self)
| 38 | self._async_initialized = False |
| 39 | |
| 40 | async def setup_async(self): |
| 41 | """Setup the LLM asynchronously.""" |
| 42 | if not self._async_initialized: |
| 43 | await self._executor.init_workers_async() |
| 44 | await self._executor.setup_engine_remote_async() |
| 45 | self._async_initialized = True |
| 46 | return self |
| 47 | |
| 48 | async def release(self, tags: list[str]): |
| 49 | """Release the GPU memory used by the LLM asynchronously. |