13 Commits

Author	SHA1	Message	Date
Peter Steinberger	da822a56d8	refactor(vllm): own nemotron thinking payloads	2026-04-27 12:15:54 +01:00
Peter Steinberger	836d4b4105	refactor(vllm): own qwen thinking payloads	2026-04-27 11:50:25 +01:00
Peter Steinberger	75c8c1bebe	fix(agents): honor qwen chat-template thinking compat	2026-04-27 11:50:24 +01:00
Peter Steinberger	f9b78fb08e	docs(models): clarify local tool call workaround	2026-04-27 10:37:52 +01:00
Peter Steinberger	1ee885123f	docs(models): document required tool choice workaround	2026-04-27 10:32:20 +01:00
Peter Steinberger	7c0fdae9b9	docs(providers): document local model request timeout	2026-04-27 05:27:41 +01:00
Peter Steinberger	ed5276f9b9	fix(providers): keep vllm nemotron replies visible	2026-04-26 03:54:20 +01:00
Vincent Koc	82a847f3b4	docs(providers): standardize Related card titles, config-reference links, and Advanced heading	2026-04-23 13:16:53 -07:00
Vincent Koc	4a2cd533ac	docs: remove duplicate H1 where frontmatter title already sets it	2026-04-23 13:11:14 -07:00
Peter Steinberger	da8621df0d	fix(openai-completions): enable local streaming usage compat (#68711) (thanks @gaineyllc)	2026-04-23 03:57:04 +01:00
Vincent Koc	e7076617f9	docs(providers): improve sglang, fal, groq, bedrock-mantle, vllm with Mintlify components	2026-04-12 11:20:58 +01:00
Peter Steinberger	edc470f6b0	docs: refresh openai compatible proxy guides	2026-04-04 09:30:57 +01:00
gejifeng	e73d881c50	Onboarding: add vLLM provider support	2026-02-13 15:48:37 +01:00