A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 7, 06:30 UTC
[Docs] Clarify structured outputs configuration for Qwen3 reasoning mode (#32441)
Signed-off-by: Davina Zaman <davzaman@users.noreply.github.com> Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Davina Zaman committed
Mar 4, 2026 at 11:44 UTC
138d891d7f42004c417561050a6813792316b13b
1 file changed
+6
docs/features/structured_outputs.md
+6
@@ -210,6 +210,12 @@ Note that you can use reasoning with any provided structured outputs feature. Th
210
211
See also: [full example](../examples/online_serving/structured_outputs.md)
212
213
+!!! note
214
+ When using Qwen3 Coder models with reasoning enabled, structured outputs might become disabled if the reasoning content does not get parsed into the `reasoning` field separately (v0.11.2+).
215
+ To use both features together, you must explicitly enable structured outputs in reasoning mode.
216
+ To do so, add the following flag when starting the vLLM server: `--structured-outputs-config.enable_in_reasoning=True`.
217
+ See also: [Reasoning Outputs](reasoning_outputs.md) documentation.
218
+
219
## Experimental Automatic Parsing (OpenAI API)
220
221
This section covers the OpenAI beta wrapper over the `client.chat.completions.create()` method that provides richer integrations with Python specific types.