From b29a026e14b9d88bcc24ced983620314d5feb13d Mon Sep 17 00:00:00 2001
From: "Simon (Jiyou) Li" <Simon-Li@users.noreply.github.com>
Date: Sat, 10 May 2025 06:50:06 +0800
Subject: [PATCH] =?UTF-8?q?KV=E2=80=91Cache=E2=80=AF(MHA,=20MLA):=20add=20?=
 =?UTF-8?q?missing=20start=5Flayer=E2=80=AF/=E2=80=AFend=5Flayer=20fields?=
 =?UTF-8?q?=20to=20MHATokenToKVPoolHost=20and=20MLATokenToKVPoolHost=20(#6?=
 =?UTF-8?q?016)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Co-authored-by: 继优 <jiyou.ljy@alibaba-inc.com>
Co-authored-by: chus-chus <chus-chus@users.noreply.github.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
---
 python/sglang/srt/mem_cache/memory_pool.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/python/sglang/srt/mem_cache/memory_pool.py b/python/sglang/srt/mem_cache/memory_pool.py
index 251d16aee..e1054e21d 100644
--- a/python/sglang/srt/mem_cache/memory_pool.py
+++ b/python/sglang/srt/mem_cache/memory_pool.py
@@ -762,6 +762,8 @@ class HostKVCache(abc.ABC):
             self.size = int(device_pool.size * host_to_device_ratio)
         # Align the host memory pool size to the page size
         self.size = self.size - (self.size % self.page_size)
+        self.start_layer = device_pool.start_layer
+        self.end_layer = device_pool.end_layer
 
         assert (
             self.size > device_pool.size