[DOC] fix: default slice_size is 64KB (#444)

doc/en/transfer-engine.md

@@ -58,7 +58,7 @@ The process involves identifying the appropriate local and target NICs based on
 
 For instance, as illustrated in figure above, to transfer data from buffer 0 (assigned to cpu:0) in the local node to buffer 1 (assigned to cpu:1) in the target node, the engine first identifies the preferred NICs for cpu:0 using the local server's topology matrix and selects one, such as mlx5_1, as the local NIC. Similarly, the target NIC, such as mlx5_3, is selected based on the target memory address. This setup enables establishing an RDMA connection from mlx5_1@local to mlx5_3@target to carry out RDMA read and write operations.
 
-To further maximize bandwidth utilization, if a single request's transfer is internally divided into multiple slices if its length exceeds 16KB. 
+To further maximize bandwidth utilization, if a single request's transfer is internally divided into multiple slices if its length exceeds 64KB. 
 Each slice might use a different path, enabling collaborative work among all RDMA NICs.
 
 ### Endpoint Management

doc/zh/transfer-engine.md

@@ -50,7 +50,7 @@ BatchTransfer API 使用请求（Request）对象数组传入用户请求，需
 
 例如，如图所示，要将数据从本地节点分配给 `cpu:0` 的缓冲区0传输到目标节点分配给`cpu:1`的缓冲区1，引擎首先使用本地服务器的拓扑矩阵识别`cpu:0`的首选NIC，并选择一个，如`mlx5_1`，作为本地NIC。同样，根据目标内存地址选择目标NIC，如`mlx5_3`。这种设置允许建立从`mlx5_1@本地`到`mlx5_3@目标`的RDMA连接，以执行RDMA读写操作。
 
-为了进一步最大化带宽利用率，如果单个请求的传输长度超过16KB，则其内部被划分为多个切片。每个切片可能使用不同的路径，使所有RDMA NIC能够协同工作。
+为了进一步最大化带宽利用率，如果单个请求的传输长度超过64KB，则其内部被划分为多个切片。每个切片可能使用不同的路径，使所有RDMA NIC能够协同工作。
 
 ### 端点管理
 Transfer Engine 使用一对端点来表示本地RDMA NIC和远程RDMA NIC之间的连接。实际上，每个端点包括一个或多个RDMA QP对象。

docs/source/design/transfer-engine.md

@@ -58,7 +58,7 @@ The process involves identifying the appropriate local and target NICs based on
 
 For instance, as illustrated in figure above, to transfer data from buffer 0 (assigned to cpu:0) in the local node to buffer 1 (assigned to cpu:1) in the target node, the engine first identifies the preferred NICs for cpu:0 using the local server's topology matrix and selects one, such as mlx5_1, as the local NIC. Similarly, the target NIC, such as mlx5_3, is selected based on the target memory address. This setup enables establishing an RDMA connection from mlx5_1@local to mlx5_3@target to carry out RDMA read and write operations.
 
-To further maximize bandwidth utilization, if a single request's transfer is internally divided into multiple slices if its length exceeds 16KB. 
+To further maximize bandwidth utilization, if a single request's transfer is internally divided into multiple slices if its length exceeds 64KB. 
 Each slice might use a different path, enabling collaborative work among all RDMA NICs.
 
 ### Endpoint Management