tests/ep: intranode send-side counts unique (token, dst_node) to match NCCL-EP

Previously total_send_tokens was Sigma over dst_rank of num_tokens_per_rank
which over-counts intra-node fan-out. NCCL-EP's ep_bench collapses
multiple destinations on the same node into one count; on a single-node
run that means total_send_tokens = number of tokens with at least one
valid expert. Switching to is_token_in_rank.any(dim=1).sum() makes the
send-side BW comparable to NCCL-EP's send: total_bw / nvl_bw line.

test/python/ext/ep/test_intranode_multirank.py

@@ -297,8 +297,14 @@ def main():
 
     # NCCL-EP `ep_bench` six-metric breakdown
     # (intranode -> single node, so rdma_*=0; nvl_*=total_*).
+    #
+    # Send side follows NCCL-EP: count unique (token, dst_node) pairs. With a
+    # single node every selected destination collapses to that node, so a
+    # token with at least one valid expert contributes exactly one to
+    # `total_send_tokens`. Recv side counts unique (src_rank, token) pairs
+    # landing on this rank.
     bytes_per_token = bench_hidden * x_b.element_size()
-    total_send_tokens_local = int(num_tokens_per_rank_b.sum().item())
+    total_send_tokens_local = int(is_token_in_rank_b.any(dim=1).sum().item())
     rdma_send_tokens_local = 0  # intranode: no remote nodes
     recv_from_src = torch.empty(num_ranks, dtype=torch.int64, device="cuda")
     dist.all_to_all_single(