[None][feat] Enable KVCacheManagerV2 by default for Llama and Llama4

docs/source/features/kvcache.md

@@ -89,6 +89,7 @@ Models that select the V2 manager by default:
 | DeepSeek-V4 | Sparse attention attaches auxiliary per-layer buffers |
 | 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); validated across text, multimodal, and disaggregated workloads |
 
 Separately, Gemma4 hybrid attention and sparse-attention models are routed to
 V2 unconditionally: their per-layer buffer layouts cannot be represented by V1's

tensorrt_llm/_torch/models/modeling_llama.py

@@ -1134,6 +1134,14 @@ def forward(
 @register_auto_model("LlamaForCausalLM")
 class LlamaForCausalLM(SpecDecOneEngineForCausalLM[LlamaModel, LlamaConfig]):
 
+    @classmethod
+    def get_preferred_kv_cache_manager_version(
+        cls,
+        pretrained_config: Any = None,
+    ) -> Literal["V2"]:
+        """Prefer KV cache manager V2 for Llama."""
+        return "V2"
+
     @classmethod
     def get_preferred_transceiver_runtime(
         cls,
@@ -1505,6 +1513,22 @@ def call_with_text_prompt(
 class Llama4ForConditionalGeneration(SpecDecOneEngineForCausalLM[Llama4Model,
                                                                  Llama4Config]):
 
+    @classmethod
+    def get_preferred_kv_cache_manager_version(
+        cls,
+        pretrained_config: Any = None,
+    ) -> Literal["V2"]:
+        """Prefer KV cache manager V2 for Llama4."""
+        return "V2"
+
+    @classmethod
+    def get_preferred_transceiver_runtime(
+        cls,
+        pretrained_config: Any = None,
+    ) -> Optional[Literal["CPP", "PYTHON"]]:
+        """Prefer the Python transceiver for Llama4 NIXL disaggregated serving."""
+        return "PYTHON"
+
     def __init__(
         self,
         model_config: ModelConfig[Llama4Config],

tests/unittest/llmapi/test_llm_args.py

@@ -711,6 +711,8 @@ def test_registered_models_prefer_v2(self):
             "Gemma4ForCausalLM",
             "Gemma4ForConditionalGeneration",
             "Gemma4UnifiedForConditionalGeneration",
+            "LlamaForCausalLM",
+            "Llama4ForConditionalGeneration",
         )
         for architecture in architectures:
             model_cls = get_registered_model_class(architecture)
@@ -751,6 +753,8 @@ def test_registered_models_keep_v2_on_nixl(self):
             "Gemma4ForCausalLM",
             "Gemma4ForConditionalGeneration",
             "Gemma4UnifiedForConditionalGeneration",
+            "LlamaForCausalLM",
+            "Llama4ForConditionalGeneration",
         )
         for architecture in architectures:
             model_cls = get_registered_model_class(architecture)