From f3a21e9c6835f04ecb5da1b953cb650986bf2209 Mon Sep 17 00:00:00 2001
From: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Date: Wed, 23 Apr 2025 16:50:05 +0100
Subject: [PATCH] `CacheConfig.block_size` should always be `int` when used
 (#17052)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
---
 vllm/config.py | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/vllm/config.py b/vllm/config.py
index 641b221f5d347..f403654be1652 100644
--- a/vllm/config.py
+++ b/vllm/config.py
@@ -1261,11 +1261,14 @@ PrefixCachingHashAlgo = Literal["builtin", "sha256"]
 class CacheConfig:
     """Configuration for the KV cache."""
 
-    block_size: Optional[BlockSize] = None
+    block_size: BlockSize = None  # type: ignore
     """Size of a contiguous cache block in number of tokens. This is ignored on
     neuron devices and set to `--max-model-len`. On CUDA devices, only block
     sizes up to 32 are supported. On HPU devices, block size defaults to 128.
-    """
+
+    This config has no static default. If left unspecified by the user, it will
+    be set in `Platform.check_and_update_configs()` based on the current
+    platform."""
     gpu_memory_utilization: float = 0.9
     """The fraction of GPU memory to be used for the model executor, which can
     range from 0 to 1. For example, a value of 0.5 would imply 50% GPU memory