Change the default num of QPs. (#263)

deep_ep/buffer.py

@@ -31,7 +31,7 @@ class Buffer:
 
     def __init__(self, group: dist.ProcessGroup,
                  num_nvl_bytes: int = 0, num_rdma_bytes: int = 0,
-                 low_latency_mode: bool = False, num_qps_per_rank: int = 12,
+                 low_latency_mode: bool = False, num_qps_per_rank: int = 24,
                  allow_nvlink_for_low_latency_mode: bool = True,
                  allow_mnnvl: bool = False) -> None:
         """