diff --git a/docs/source/features/kvcache.md b/docs/source/features/kvcache.md
index a78adfa36c02..56b6b1301536 100644
--- a/docs/source/features/kvcache.md
+++ b/docs/source/features/kvcache.md
@@ -90,6 +90,7 @@ Models that select the V2 manager by default:
 | GPT-OSS | Sliding window on every other layer (VSWA), so the sliding-window and full-attention pools are sized independently |
 | Gemma3 / Gemma4 (text and multimodal) | Alternating sliding-window and full-attention layers (VSWA); same independent pool sizing |
 | Llama / Llama4 | Uniform KV pool layout; chunked attention does not partition the pools |
+| KimiLinear | Hybrid KDA recurrent state and paged MLA cache |
 
 Separately, Gemma4 hybrid attention and sparse-attention models are routed to
 V2 unconditionally: their per-layer buffer layouts cannot be represented by V1's
diff --git a/tensorrt_llm/_torch/models/modeling_kimi_linear.py b/tensorrt_llm/_torch/models/modeling_kimi_linear.py
index 60d840506301..dc409bcb18ed 100644
--- a/tensorrt_llm/_torch/models/modeling_kimi_linear.py
+++ b/tensorrt_llm/_torch/models/modeling_kimi_linear.py
@@ -18,7 +18,7 @@
 
 Caching
 -------
-KDA states live on the mamba side of a ``MixedMambaHybridCacheManager``
+KDA states live on the mamba side of a ``MambaHybridCacheManagerV2``
 (wired in ``pyexecutor/_util.py``): per layer, a short-conv slot of
 ``[3 * num_heads * head_dim, W]`` bf16 (the full FLA ``ShortConvolution``
 cache window, sections ``[q | k | v]``) and a delta-rule recurrent slot of
@@ -68,13 +68,12 @@
 and the MLA prefill path natively attends over the cached latent prefix
 (``kv_len = cached + q_len``). KV-cache block reuse is supported as an
 opt-in via ``kv_cache_config.enable_block_reuse=true``, which routes to
-the unified-pool ``CppMambaHybridCacheManager`` (per-block KDA state
-snapshots every ``mamba_state_cache_interval`` tokens, FORCE_CHUNK
-context chunking).
+``MambaHybridCacheManagerV2`` (per-block KDA state snapshots every
+``mamba_state_cache_interval`` tokens, FORCE_CHUNK context chunking).
 
 Not supported: pipeline parallelism, draft-head spec-dec modes
 (MTP/Eagle — no draft-head checkpoint exists). SA speculative decoding
-is validated only without block reuse (Mixed cache manager).
+is validated only without block reuse.
 """
 
 from __future__ import annotations
@@ -2103,9 +2102,7 @@ def _setup_helix_mappings(
     @classmethod
     def get_model_defaults(cls, llm_args) -> dict:
         # - enable_block_reuse defaults off: reuse is supported as an
-        #   explicit opt-in (routes to CppMambaHybridCacheManager with
-        #   per-block KDA state snapshots); the default stays on the
-        #   Mixed manager, which SA speculative decoding requires.
+        #   explicit opt-in with per-block KDA state snapshots.
         # - tokens_per_block=64: with 32, the flashinfer trtllm-gen FMHA lib
         #   rejects the MLA (576, 512) generation kernel (marked slower) and
         #   the fallback C++ path requires num_heads % 64 == 0, which K3's
@@ -2117,6 +2114,14 @@ def get_model_defaults(cls, llm_args) -> dict:
             }
         }
 
+    @classmethod
+    def get_preferred_kv_cache_manager_version(
+        cls,
+        pretrained_config: Any = None,
+    ) -> Literal["V2"]:
+        """Prefer KV cache manager V2 for KimiLinear."""
+        return "V2"
+
     @classmethod
     def get_preferred_transceiver_runtime(
         cls,
diff --git a/tests/unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py b/tests/unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py
index d9902377405b..c2b18556b718 100644
--- a/tests/unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py
+++ b/tests/unittest/_torch/executor/kv_cache/test_mamba_cache_manager.py
@@ -844,10 +844,10 @@ def test_qwen3_gdn_replay_uses_v2_preference(
     )
 
 
-def test_kimi_without_v2_preference_uses_mixed_manager(
+def test_kimi_model_preference_uses_v2_manager(
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
-    """Kimi K3 uses separate KV and recurrent-state pools for SA decoding."""
+    """Kimi's model preference selects V2 for its KDA and MLA cache."""
     from tensorrt_llm._torch.models.modeling_kimi_linear import KimiLinearForCausalLM
 
     monkeypatch.delenv("TRTLLM_USE_PY_MAMBA", raising=False)
@@ -862,13 +862,13 @@ def test_kimi_without_v2_preference_uses_mixed_manager(
     )
     resolved = _resolve_kv_cache_manager_v2_auto(llm_args, KimiLinearForCausalLM)
 
-    assert resolved is False
-    assert llm_args.kv_cache_config.use_kv_cache_manager_v2 is False
+    assert resolved is True
+    assert llm_args.kv_cache_config.use_kv_cache_manager_v2 is True
     assert llm_args.kv_cache_config.enable_block_reuse is False
     assert llm_args.kv_cache_config.tokens_per_block == 64
     assert (
         get_kv_cache_manager_cls(_kimi_model_config(), llm_args.kv_cache_config)
-        is MixedMambaHybridCacheManager
+        is MambaHybridCacheManagerV2
     )
 
 
diff --git a/tests/unittest/llmapi/test_llm_args.py b/tests/unittest/llmapi/test_llm_args.py
index c1e09bd89930..152efe3b11e6 100644
--- a/tests/unittest/llmapi/test_llm_args.py
+++ b/tests/unittest/llmapi/test_llm_args.py
@@ -827,6 +827,7 @@ def test_registered_models_prefer_v2(self) -> None:
             "MistralLarge3ForCausalLM",
             "DeepseekV4ForCausalLM",
             "KimiK25ForConditionalGeneration",
+            "KimiLinearForCausalLM",
             "MiniMaxM2ForCausalLM",
             "NemotronHForCausalLM",
             "NemotronHPuzzleForCausalLM",
@@ -871,6 +872,7 @@ def test_registered_models_keep_v2_on_nixl(self) -> None:
             "MistralLarge3ForCausalLM",
             "GptOssForCausalLM",
             "KimiK25ForConditionalGeneration",
+            "KimiLinearForCausalLM",
             "NemotronHForCausalLM",
             "NemotronHPuzzleForCausalLM",
             "Qwen3NextForCausalLM",