Ilya Kolchinsky deee355952 fix: Added lazy initialization of the remote vLLM client to avoid issues with expired asyncio event loop (#1969) ... # What does this PR do? Closes #1968. The asynchronous client in `VLLMInferenceAdapter` is now initialized directly before first use and not in `VLLMInferenceAdapter.initialize`. This prevents issues arising due to accessing an expired event loop from a completed `asyncio.run`. ## Test Plan Ran unit tests, including `test_remote_vllm.py`. Ran the code snippet mentioned in #1968. --------- Co-authored-by: Sébastien Han <seb@redhat.com>		2025-04-23 15:33:19 +02:00
..
apis	feat(agents): add agent naming functionality (#1922)	2025-04-17 07:02:47 -07:00
cli	feat: allow building distro with external providers (#1967)	2025-04-18 17:18:28 +02:00
distribution	feat: Hide tool output under an expander in Playground UI (#2003)	2025-04-23 15:32:12 +02:00
models	fix: OAI compat endpoint for meta reference inference provider (#1962)	2025-04-17 11:16:04 -07:00
providers	fix: Added lazy initialization of the remote vLLM client to avoid issues with expired asyncio event loop (#1969)	2025-04-23 15:33:19 +02:00
strong_typing	chore: more mypy checks (ollama, vllm, ...) (#1777)	2025-04-01 17:12:39 +02:00
templates	feat: Update NVIDIA to GA docs; remove notebook reference until ready (#1999)	2025-04-18 19:13:18 -04:00
__init__.py	export LibraryClient	2024-12-13 12:08:00 -08:00
env.py	refactor(test): move tools, evals, datasetio, scoring and post training tests (#1401)	2025-03-04 14:53:47 -08:00
log.py	chore: Remove style tags from log formatter (#1808)	2025-03-27 10:18:21 -04:00
schema_utils.py	fix: dont check protocol compliance for experimental methods	2025-04-12 16:26:32 -07:00