[Feature] Xiaomi MiMo-V2-Flash day0 support (#15207)

Co-authored-by: 谢学扬 <xiexueyang@xiaomi.com>
Co-authored-by: tz <tangzhen3@xiaomi.com>
Co-authored-by: 李家乐 <lijiale10@xiaomi.com>
Co-authored-by: 张晨 <zhangchen50@xiaomi.com>
Co-authored-by: Shaohui Liu <liushaohui3@xiaomi.com>
Co-authored-by: 王晨 <wangchen77@xiaomi.com>
Co-authored-by: jiangzihan <jiangzihan@xiaomi.com>
Co-authored-by: xiexueyang <xyxie_wangyi@163.com>
Co-authored-by: Linghao Zhang <zhanglinghao@xiaomi.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
Co-authored-by: JoyFuture <35593546+JoyFuture@users.noreply.github.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
Co-authored-by: Qiaolin Yu <liin1211@outlook.com>
Co-authored-by: root <root@bj9-ml-g8h20e-k8s-slave106-20251106.alicn.idc.xiaomi.com>

python/sglang/srt/mem_cache/chunk_cache.py

@@ -82,6 +82,7 @@ class SWAChunkCache(ChunkCache):
     def __init__(self, params: CacheInitParams):
         assert isinstance(params.token_to_kv_pool_allocator, SWATokenToKVPoolAllocator)
         super().__init__(params)
+        self.is_local_attention = params.is_local_attention
 
     def evict_swa(
         self,
@@ -89,10 +90,14 @@ class SWAChunkCache(ChunkCache):
         prelen: int,
         attention_chunk_size: int,
     ):
-        if prelen >= req.evicted_seqlen_local + attention_chunk_size:
-            new_evicted_seqlen_local = attention_chunk_size * (
-                prelen // attention_chunk_size
-            )
+        thresh = req.evicted_seqlen_local + attention_chunk_size * 2
+        if self.is_local_attention:
+            thresh -= attention_chunk_size
+
+        if prelen >= thresh:
+            new_evicted_seqlen_local = (
+                prelen // attention_chunk_size * attention_chunk_size
+            ) - (attention_chunk_size if not self.is_local_attention else 0)
             free_slots = self.req_to_token_pool.req_to_token[
                 req.req_pool_idx, req.evicted_seqlen_local : new_evicted_seqlen_local
             ]