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