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
..
anthropic	feat(providers): Groq now uses LiteLLM openai-compat (#1303)	2025-02-27 13:16:50 -08:00
bedrock	fix: 100% OpenAI API verification for together and fireworks (#1946)	2025-04-14 08:56:29 -07:00
cerebras	fix: 100% OpenAI API verification for together and fireworks (#1946)	2025-04-14 08:56:29 -07:00
cerebras_openai_compat	test: verification on provider's OAI endpoints (#1893)	2025-04-07 23:06:28 -07:00
databricks	fix: 100% OpenAI API verification for together and fireworks (#1946)	2025-04-14 08:56:29 -07:00
fireworks	fix: OpenAI Completions API and Fireworks (#1997)	2025-04-21 11:49:12 -07:00
fireworks_openai_compat	test: verification on provider's OAI endpoints (#1893)	2025-04-07 23:06:28 -07:00
gemini	feat(providers): Groq now uses LiteLLM openai-compat (#1303)	2025-02-27 13:16:50 -08:00
groq	fix: 100% OpenAI API verification for together and fireworks (#1946)	2025-04-14 08:56:29 -07:00
groq_openai_compat	test: verification on provider's OAI endpoints (#1893)	2025-04-07 23:06:28 -07:00
nvidia	feat: update nvidia inference provider to use model_store (#1988)	2025-04-18 10:16:43 +02:00
ollama	feat: allow ollama to use 'latest' if available but not specified (#1903)	2025-04-14 09:03:54 -07:00
openai	feat(providers): Groq now uses LiteLLM openai-compat (#1303)	2025-02-27 13:16:50 -08:00
passthrough	fix: 100% OpenAI API verification for together and fireworks (#1946)	2025-04-14 08:56:29 -07:00
runpod	fix: 100% OpenAI API verification for together and fireworks (#1946)	2025-04-14 08:56:29 -07:00
sambanova	fix: 100% OpenAI API verification for together and fireworks (#1946)	2025-04-14 08:56:29 -07:00
sambanova_openai_compat	test: verification on provider's OAI endpoints (#1893)	2025-04-07 23:06:28 -07:00
tgi	fix: 100% OpenAI API verification for together and fireworks (#1946)	2025-04-14 08:56:29 -07:00
together	fix: Together provider shutdown and default to non-streaming (#2001)	2025-04-22 17:47:53 +02:00
together_openai_compat	test: verification on provider's OAI endpoints (#1893)	2025-04-07 23:06:28 -07:00
vllm	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
__init__.py	impls -> inline, adapters -> remote (#381)	2024-11-06 14:54:05 -08:00