diff --git a/collectivex/bench/ep_deepep_v2.py b/collectivex/bench/ep_deepep_v2.py
index e6a7472752..b31b79fbac 100644
--- a/collectivex/bench/ep_deepep_v2.py
+++ b/collectivex/bench/ep_deepep_v2.py
@@ -136,7 +136,7 @@ class DeepEPV2Backend(LegacyBufferLL, EPBackend):
     # vLLM's low-latency send/receive split (see LegacyBufferLL).
     ll_recv_hook = True
     # The num_sms the timed dispatch passes: 0 hands the count to DeepEP's model, as vLLM does;
-    # create_buffer overrides it only on EFA.
+    # create_buffer overrides it where the registry sets rdma_gbs.
     _dispatch_num_sms = 0
 
     @staticmethod
@@ -380,7 +380,7 @@ def dispatch(self, p):
             num_experts=self.args.experts,
             num_max_tokens_per_rank=self._dispatch_capacity(p.T),
             expert_alignment=1,
-            num_sms=self._dispatch_num_sms,  # 0 (DeepEP's model) except on EFA; see create_buffer
+            num_sms=self._dispatch_num_sms,  # 0 (DeepEP's model) unless rdma_gbs is set
             async_with_compute_stream=False,
             do_handle_copy=True,
             do_cpu_sync=False,
diff --git a/collectivex/configs/platform_config.json b/collectivex/configs/platform_config.json
index ecc13310a1..1dd176dcc0 100644
--- a/collectivex/configs/platform_config.json
+++ b/collectivex/configs/platform_config.json
@@ -65,7 +65,8 @@
       },
       "network": {
         "socket_ifname": "bond0",
-        "rdma_devices": "mlx5_0,mlx5_1,mlx5_2,mlx5_3,mlx5_4,mlx5_5,mlx5_10,mlx5_11"
+        "rdma_devices": "mlx5_0,mlx5_1,mlx5_2,mlx5_3,mlx5_4,mlx5_5,mlx5_10,mlx5_11",
+        "rdma_gbs": 50
       }
     },
     "b300": {
diff --git a/collectivex/docs/methodology.md b/collectivex/docs/methodology.md
index 9e01236503..6b3a0af9f6 100644
--- a/collectivex/docs/methodology.md
+++ b/collectivex/docs/methodology.md
@@ -182,8 +182,8 @@ when the LSA team is smaller than the world. x86 EP16 is that hybrid path, GIN a
 domains of eight scale-up ranks each. GB EP16 stays inside MNNVL and uses LSA. Hybrid EP16 allocates
 33 GIN QPs per peer (a fixed 512-QP budget) instead of the automatic 65/129, which exhausts the
 per-NIC QP budget on CX-7. DeepEP's SM model reads the scale-out rate from an `ibstat` probe that cannot
-see EFA and that the vLLM image does not ship, so on the EFA pools and on h200-dgxc the registry's
-`network.rdma_gbs` supplies the per-GPU rate and the resulting count is passed explicitly
+see EFA and that the vLLM image does not ship, so on the EFA pools, h200-dgxc and b200-nscale the
+registry's `network.rdma_gbs` supplies the per-GPU rate and the resulting count is passed explicitly
 (`library_config.sm_model_rdma_gbs`).
 
 **A virtualized pool can make a scale-out row measure the hypervisor.** ElasticBuffer registers its GIN