From 05af7b072c64a738178924e5a0dbd54c9f03e6d1 Mon Sep 17 00:00:00 2001
From: pos-ei-don <1822533+pos-ei-don@users.noreply.github.com>
Date: Sat, 24 Oct 2026 19:30:35 +0000
Subject: [PATCH] docs(vllm): explain sampling validation

Describe stop strings, greedy decoding, and seed handling after sampling
parameters are validated during construction.

Signed-off-by: pos-ei-don <1822533+pos-ei-don@users.noreply.github.com>
---
 docs/content/advanced/model-configuration.md | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/docs/content/advanced/model-configuration.md b/docs/content/advanced/model-configuration.md
index bea83b6f5..5fd89323c 100644
--- a/docs/content/advanced/model-configuration.md
+++ b/docs/content/advanced/model-configuration.md
@@ -833,6 +833,12 @@ The fields below come from upstream llama.cpp's **CLI completion tool** and are
 
 These options apply when using the `vllm` backend:
 
+The `vllm` backend validates sampling parameters before generation. Stop strings
+work with streaming and non-streaming requests; an empty stop string is invalid.
+Presence and frequency penalties must be between -2 and 2. A temperature of `0`
+selects greedy decoding, which ignores `top_p` and `top_k`. A seed of `-1` uses
+vLLM's default random seed behavior.
+
 | Field | Type | Description |
 |-------|------|-------------|
 | `gpu_memory_utilization` | float32 | GPU memory utilization (0.0-1.0, default 0.9) |