dsv4.1: remaining model and runtime integration (#38798)

Co-authored-by: BBuf <1182563586@qq.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Xiaoyu Zhang <xiaoyu.zhang@radixark.ai>
Co-authored-by: Yuwei An <ayw.sirius19@gmail.com>
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: Zhichen Zeng <zczeng@uw.edu>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>

test/registered/unit/disaggregation/test_admission_abort_not_enqueued.py

@@ -86,6 +86,7 @@ def _prefill_queue(sched):
 def _decode_queue(sched):
     q = SimpleNamespace(
         scheduler=sched,
+        token_to_kv_pool_allocator=MagicMock(),
         retracted_queue=[],
         pending_reqs=[],
         _check_if_req_exceed_kv_capacity=MagicMock(return_value=False),

test/registered/unit/disaggregation/test_disaggregation_wire.py

@@ -906,7 +906,7 @@ def _buf_infos(*ptrs):
 
 def _make_dsv4_target(*, unified, mapping=None):
     pool = object.__new__(DeepSeekV4TokenToKVPool)
-    pool.compression_ratios = [0, 4, 128]
+    pool.compression_ratios = [0, 2, 1, 4, 128]
     pool._unified_kv = unified
     pool.page_size = 256
     pool.sliding_window = 128