From 88e7c8683628cb1ff4d766d83b049e372a1dbb02 Mon Sep 17 00:00:00 2001 From: Grendgi Date: Tue, 9 Jun 2026 13:49:27 +0300 Subject: [PATCH] Document vLLM audio URL payloads --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index be1740d..e101cec 100644 --- a/README.md +++ b/README.md @@ -59,8 +59,8 @@ Recommended comparison order: 3. `voxtral-small` (`mistralai/Voxtral-Small-24B-2507`) Qwen2-Audio and Voxtral are called through an OpenAI-compatible -`/v1/chat/completions` endpoint with `input_audio`; set their endpoint URLs only -after the models are actually exposed on the AI server. +`/v1/chat/completions` endpoint with vLLM-style `audio_url` data URLs; set +their endpoint URLs only after the models are actually exposed on the AI server. AI-server compose snippets for these temporary comparison endpoints live in `deploy/ai-server/docker-compose.audio.yml`. They are profile-gated because the