KV‑Cache (MHA, MLA): add missing start_layer / end_layer fields to MHATokenToKVPoolHost and MLATokenToKVPoolHost (#6016)

Co-authored-by: 继优 <[email protected]>
Co-authored-by: chus-chus <[email protected]>
Co-authored-by: Zhiqiang Xie <[email protected]>

Author: 4 people

python/sglang/srt/mem_cache/memory_pool.py

@@ -762,6 +762,8 @@ def __init__(
             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