Add RPC longhaul paging

tools/rpc/README.md

@@ -36,6 +36,17 @@ flowchart TD
 By default, `ggml-rpc-server` exposes all available accelerator devices on the host.
 If there are no accelerators, it exposes a single `CPU` device.
 
+For server-resident longhaul MoE paging, place the same GGUF shards on the RPC
+host and point the server at their directory:
+
+```sh
+$ bin/ggml-rpc-server --device MTL0 --longhaul-root /path/to/model-directory
+```
+
+The client can then use `--rpc`, `--longhaul`, and `--longhaul-cache` together.
+RPC longhaul v1 requires one remote Metal device. Expert cache misses are read
+from the RPC host's local files rather than uploaded by the client.
+
 ## Usage
 
 ### Remote hosts
@@ -107,4 +118,3 @@ Use the `GGML_RPC_DEBUG` environment variable to enable debug messages from `ggm
 ```bash
 $ GGML_RPC_DEBUG=1 bin/ggml-rpc-server
 ```
-