update llama-rpc-server bin name + doc

Author: Olivier Chafik

Makefile

@@ -106,7 +106,7 @@ ifeq ($(UNAME_S),Darwin)
 endif
 
 ifdef LLAMA_RPC
-	BUILD_TARGETS += rpc-server
+	BUILD_TARGETS += llama-rpc-server
 endif
 
 default: $(BUILD_TARGETS)
@@ -699,7 +699,7 @@ ggml-rpc.o: ggml-rpc.cpp ggml-rpc.h
 rpc-server.o: examples/rpc/rpc-server.cpp ggml-rpc.h
 	$(CXX) $(CXXFLAGS) -c $< -o $@
 
-rpc-server: rpc-server.o ggml.o llama.o $(COMMON_DEPS) $(OBJS)
+llama-rpc-server: rpc-server.o ggml.o llama.o $(COMMON_DEPS) $(OBJS)
 	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
 endif # LLAMA_RPC
 

examples/rpc/CMakeLists.txt

@@ -1,2 +1,3 @@
-add_executable(rpc-server rpc-server.cpp)
-target_link_libraries(rpc-server PRIVATE ggml llama)
+set(TARGET llama-rpc-server)
+add_executable(${TARGET} rpc-server.cpp)
+target_link_libraries(${TARGET} PRIVATE ggml llama)

examples/rpc/README.md

@@ -1,7 +1,7 @@
 ## Overview
 
-The `rpc-server` allows  running `ggml` backend on a remote host.
-The RPC backend communicates with one or several instances of `rpc-server` and offloads computations to them.
+`llama-rpc-server` allows  running `ggml` backend on a remote host.
+The RPC backend communicates with one or several instances of `llama-rpc-server` and offloads computations to them.
 This can be used for distributed LLM inference with `llama.cpp` in the following way:
 
 ```mermaid
@@ -10,13 +10,13 @@ flowchart TD
     rpcb---|TCP|srvb
     rpcb-.-|TCP|srvn
     subgraph hostn[Host N]
-    srvn[rpc-server]-.-backend3["Backend (CUDA,Metal,etc.)"]
+    srvn[llama-rpc-server]-.-backend3["Backend (CUDA,Metal,etc.)"]
     end
     subgraph hostb[Host B]
-    srvb[rpc-server]---backend2["Backend (CUDA,Metal,etc.)"]
+    srvb[llama-rpc-server]---backend2["Backend (CUDA,Metal,etc.)"]
     end
     subgraph hosta[Host A]
-    srva[rpc-server]---backend["Backend (CUDA,Metal,etc.)"]
+    srva[llama-rpc-server]---backend["Backend (CUDA,Metal,etc.)"]
     end
     subgraph host[Main Host]
     ggml[llama.cpp]---rpcb[RPC backend]
@@ -25,24 +25,22 @@ flowchart TD
 ```
 
 Each host can run a different backend, e.g. one with CUDA and another with Metal.
-You can also run multiple `rpc-server` instances on the same host, each with a different backend.
+You can also run multiple `llama-rpc-server` instances on the same host, each with a different backend.
 
 ## Usage
 
 On each host, build the corresponding backend with `cmake` and add `-DLLAMA_RPC=ON` to the build options.
 For example, to build the CUDA backend with RPC support:
 
 ```bash
-mkdir build-rpc-cuda
-cd build-rpc-cuda
-cmake .. -DLLAMA_CUDA=ON -DLLAMA_RPC=ON
-cmake --build . --config Release
+cmake -B build-rpc-cuda -DLLAMA_CUDA=ON -DLLAMA_RPC=ON
+cmake --build build-rpc-cuda --config Release
 ```
 
-Then, start the `rpc-server` with the backend:
+Then, start `llama-rpc-server` with the backend:
 
 ```bash
-$ bin/rpc-server -p 50052
+$ bin/llama-rpc-server -p 50052
 create_backend: using CUDA backend
 ggml_cuda_init: GGML_CUDA_FORCE_MMQ:   no
 ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
@@ -53,21 +51,19 @@ Starting RPC server on 0.0.0.0:50052
 
 When using the CUDA backend, you can specify the device with the `CUDA_VISIBLE_DEVICES` environment variable, e.g.:
 ```bash
-$ CUDA_VISIBLE_DEVICES=0 bin/rpc-server -p 50052
+$ CUDA_VISIBLE_DEVICES=0 bin/llama-rpc-server -p 50052
 ```
-This way you can run multiple `rpc-server` instances on the same host, each with a different CUDA device.
+This way you can run multiple `llama-rpc-server` instances on the same host, each with a different CUDA device.
 
 
 On the main host build `llama.cpp` only with `-DLLAMA_RPC=ON`:
 
 ```bash
-mkdir build-rpc
-cd build-rpc
-cmake .. -DLLAMA_RPC=ON
-cmake --build . --config Release
+cmake -B build-rpc -DLLAMA_RPC=ON
+cmake --build build-rpc --config Release -t -j
 ```
 
-Finally, use the `--rpc` option to specify the host and port of each `rpc-server`:
+Finally, use the `--rpc` option to specify the host and port of each `llama-rpc-server`:
 
 ```bash
 $ bin/llama-cli -m ../models/tinyllama-1b/ggml-model-f16.gguf -p "Hello, my name is" --repeat-penalty 1.0 -n 64 --rpc 192.168.88.10:50052,192.168.88.11:50052 -ngl 99