diff --git a/tensorrt_llm/_torch/pyexecutor/_util.py b/tensorrt_llm/_torch/pyexecutor/_util.py
index 0149ba7ae03a..4c743dfbe5a4 100644
--- a/tensorrt_llm/_torch/pyexecutor/_util.py
+++ b/tensorrt_llm/_torch/pyexecutor/_util.py
@@ -342,6 +342,31 @@ def __init__(
                                                   KVCacheManagerV2)
         self._draft_config = draft_config
         self._skip_est = skip_est
+        self._maybe_enable_fabric_memory_for_python_transceiver()
+
+    def _maybe_enable_fabric_memory_for_python_transceiver(self):
+        """Default TRTLLM_KVCACHE_POOL_USE_FABRIC_MEMORY=1 for the Python
+        transceiver on the C++ V1 KV cache manager.
+
+        The Python transceiver (KvCacheTransceiverV2) transfers KV blocks
+        directly out of the C++ pool, so the pool should be allocated with
+        fabric memory to enable MNNVL transfers. This must run before any
+        pool allocation because the C++ env getter caches the value on first
+        read. Explicit user settings are respected, and platforms without
+        fabric memory support fall back to standard allocation in C++.
+        """
+        if (self._cache_transceiver_config is None
+                or self._cache_transceiver_config.backend is None or
+                self._cache_transceiver_config.transceiver_runtime != "PYTHON"):
+            return
+        if not issubclass(self._kv_cache_manager_cls, KVCacheManager):
+            return
+        if os.environ.get("TRTLLM_KVCACHE_POOL_USE_FABRIC_MEMORY") is None:
+            os.environ["TRTLLM_KVCACHE_POOL_USE_FABRIC_MEMORY"] = "1"
+            logger.info(
+                "Python cache transceiver with C++ KV cache manager detected; "
+                "defaulting TRTLLM_KVCACHE_POOL_USE_FABRIC_MEMORY=1 (set it "
+                "to 0 explicitly to disable)")
 
     def _get_model_kv_cache_manager_cls(
         self,
diff --git a/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_1k1k_con64_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml b/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_1k1k_con64_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
index 9c82b55a4a17..53736a99c780 100644
--- a/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_1k1k_con64_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
+++ b/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_1k1k_con64_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
@@ -63,6 +63,7 @@ worker_config:
       max_tokens_in_buffer: 1024
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
     num_postprocess_workers: 4
     stream_interval: 20
@@ -88,4 +89,5 @@ worker_config:
       max_tokens_in_buffer: 1024
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
diff --git a/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con1024_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml b/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con1024_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
index 9f4b7086060d..ffa8cdfa4522 100644
--- a/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con1024_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
+++ b/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con1024_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
@@ -75,6 +75,7 @@ worker_config:
       max_tokens_in_buffer: 9216
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: false
     num_postprocess_workers: 4
     stream_interval: 20
@@ -103,6 +104,7 @@ worker_config:
       max_tokens_in_buffer: 9216
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
     num_postprocess_workers: 4
     stream_interval: 20
diff --git a/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con128_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml b/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con128_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
index c9f73573fcf9..3f00a0063523 100644
--- a/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con128_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
+++ b/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con128_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
@@ -63,6 +63,7 @@ worker_config:
       max_tokens_in_buffer: 8448
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
     num_postprocess_workers: 4
     stream_interval: 20
@@ -88,4 +89,5 @@ worker_config:
       max_tokens_in_buffer: 8448
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
diff --git a/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con4_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml b/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con4_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
index 9610d4a5bdf9..edca66a96d87 100644
--- a/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con4_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
+++ b/tests/scripts/perf-sanity/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con4_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
@@ -63,6 +63,7 @@ worker_config:
       max_tokens_in_buffer: 8448
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
     num_postprocess_workers: 4
     stream_interval: 20
@@ -88,4 +89,5 @@ worker_config:
       max_tokens_in_buffer: 8448
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
diff --git a/tests/scripts/perf/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con1024_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml b/tests/scripts/perf/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con1024_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
index 9f4b7086060d..ffa8cdfa4522 100644
--- a/tests/scripts/perf/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con1024_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
+++ b/tests/scripts/perf/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con1024_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
@@ -75,6 +75,7 @@ worker_config:
       max_tokens_in_buffer: 9216
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: false
     num_postprocess_workers: 4
     stream_interval: 20
@@ -103,6 +104,7 @@ worker_config:
       max_tokens_in_buffer: 9216
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
     num_postprocess_workers: 4
     stream_interval: 20
diff --git a/tests/scripts/perf/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con128_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml b/tests/scripts/perf/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con128_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
index 9ed015cd6cda..afa141b6ae82 100644
--- a/tests/scripts/perf/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con128_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
+++ b/tests/scripts/perf/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con128_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
@@ -74,6 +74,7 @@ worker_config:
       max_tokens_in_buffer: 8448
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
     num_postprocess_workers: 4
     stream_interval: 20
@@ -99,4 +100,5 @@ worker_config:
       max_tokens_in_buffer: 8448
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
diff --git a/tests/scripts/perf/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con4_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml b/tests/scripts/perf/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con4_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
index 5476fae34c0e..c8dffadebfa7 100644
--- a/tests/scripts/perf/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con4_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
+++ b/tests/scripts/perf/disaggregated/gb200_gpt-oss-120b-fp4_8k1k_con4_ctx1_tp1_gen1_tp4_eplb0_mtp0_ccb-NIXL.yaml
@@ -74,6 +74,7 @@ worker_config:
       max_tokens_in_buffer: 8448
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
     num_postprocess_workers: 4
     stream_interval: 20
@@ -99,4 +100,5 @@ worker_config:
       max_tokens_in_buffer: 8448
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
diff --git a/tests/scripts/perf/disaggregated/gb200_stress-gpt-oss-120b-fp4_8k1k_ctx1_tp1_gen1_tp4_eplb0_eagle3_ccb-NIXL.yaml b/tests/scripts/perf/disaggregated/gb200_stress-gpt-oss-120b-fp4_8k1k_ctx1_tp1_gen1_tp4_eplb0_eagle3_ccb-NIXL.yaml
index 0701596a0bad..9e9dd0877c90 100644
--- a/tests/scripts/perf/disaggregated/gb200_stress-gpt-oss-120b-fp4_8k1k_ctx1_tp1_gen1_tp4_eplb0_eagle3_ccb-NIXL.yaml
+++ b/tests/scripts/perf/disaggregated/gb200_stress-gpt-oss-120b-fp4_8k1k_ctx1_tp1_gen1_tp4_eplb0_eagle3_ccb-NIXL.yaml
@@ -80,6 +80,7 @@ worker_config:
       max_tokens_in_buffer: 8448
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
     speculative_config: &id001
       decoding_type: Eagle
@@ -110,5 +111,6 @@ worker_config:
       max_tokens_in_buffer: 8448
       backend: NIXL
       transceiver_runtime: PYTHON
+      kv_cache_bounce_size_mb: 512
     disable_overlap_scheduler: true
     speculative_config: *id001