From c299a92c38b6de6a1139617652b66081828648db Mon Sep 17 00:00:00 2001 From: Christian Kastner Date: Sat, 27 Jun 2026 09:31:29 +0200 Subject: [PATCH] binaries : Improve rpc-server and export-graph-ops names. (#25045) Tests are generally prefixed with -test, so rename export-graph-ops accordingly. rpc-server is probably too generic a name for /usr/bin. Because it should work with any ggml application, it is renamed to ggml-rpc-server. --- SECURITY.md | 2 +- tests/CMakeLists.txt | 8 ++--- tests/test-backend-ops.cpp | 2 +- ...raph-ops.cpp => test-export-graph-ops.cpp} | 2 +- tools/rpc/CMakeLists.txt | 2 +- tools/rpc/README.md | 34 +++++++++---------- 6 files changed, 25 insertions(+), 25 deletions(-) rename tests/{export-graph-ops.cpp => test-export-graph-ops.cpp} (98%) diff --git a/SECURITY.md b/SECURITY.md index a98b8e70bd..0e704e3280 100644 --- a/SECURITY.md +++ b/SECURITY.md @@ -80,7 +80,7 @@ To protect sensitive data from potential leaks or unauthorized access, it is cru ### Untrusted environments or networks If you can't run your models in a secure and isolated environment or if it must be exposed to an untrusted network, make sure to take the following security precautions: -* Do not use the RPC backend, [rpc-server](https://github.com/ggml-org/llama.cpp/tree/master/tools/rpc) and [llama-server](https://github.com/ggml-org/llama.cpp/tree/master/tools/server) functionality (see https://github.com/ggml-org/llama.cpp/pull/13061). +* Do not use the RPC backend, [ggml-rpc-server](https://github.com/ggml-org/llama.cpp/tree/master/tools/rpc) and [llama-server](https://github.com/ggml-org/llama.cpp/tree/master/tools/server) functionality (see https://github.com/ggml-org/llama.cpp/pull/13061). * Confirm the hash of any downloaded artifact (e.g. pre-trained model weights) matches a known-good value. * Encrypt your data if sending it over the network. diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt index 0dd1d7b162..24592a2792 100644 --- a/tests/CMakeLists.txt +++ b/tests/CMakeLists.txt @@ -302,9 +302,9 @@ target_link_libraries(${TEST_TARGET} PRIVATE llama) llama_build_and_test(test-alloc.cpp) target_include_directories(test-alloc PRIVATE ${PROJECT_SOURCE_DIR}/ggml/src) -llama_build(export-graph-ops.cpp) -target_include_directories(export-graph-ops PRIVATE ${PROJECT_SOURCE_DIR}/ggml/src) +llama_build(test-export-graph-ops.cpp) +target_include_directories(test-export-graph-ops PRIVATE ${PROJECT_SOURCE_DIR}/ggml/src) if (TARGET gguf-model-data) - target_link_libraries(export-graph-ops PRIVATE gguf-model-data) - target_compile_definitions(export-graph-ops PRIVATE LLAMA_HF_FETCH) + target_link_libraries(test-export-graph-ops PRIVATE gguf-model-data) + target_compile_definitions(test-export-graph-ops PRIVATE LLAMA_HF_FETCH) endif() diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp index 0830dbf570..09ac62a756 100644 --- a/tests/test-backend-ops.cpp +++ b/tests/test-backend-ops.cpp @@ -9943,7 +9943,7 @@ static void usage(char ** argv) { printf(" --output specifies output format (default: console, options: console, sql, csv)\n"); printf(" --list-ops lists all available GGML operations\n"); printf(" --show-coverage shows test coverage\n"); - printf(" --test-file reads test operators from a test file generated by llama-export-graph-ops\n"); + printf(" --test-file reads test operators from a test file generated by test-export-graph-ops\n"); printf(" -j runs tests using parallel worker threads (default: 1, test mode only)\n"); } diff --git a/tests/export-graph-ops.cpp b/tests/test-export-graph-ops.cpp similarity index 98% rename from tests/export-graph-ops.cpp rename to tests/test-export-graph-ops.cpp index 64cf6dcea3..7d8118dcd6 100644 --- a/tests/export-graph-ops.cpp +++ b/tests/test-export-graph-ops.cpp @@ -185,7 +185,7 @@ int main(int argc, char ** argv) { return 1; } #else - LOG_ERR("export-graph-ops compiled without HF fetch support\n"); + LOG_ERR("test-export-graph-ops compiled without HF fetch support\n"); return 1; #endif } diff --git a/tools/rpc/CMakeLists.txt b/tools/rpc/CMakeLists.txt index 20f114ad9b..0eee9a922e 100644 --- a/tools/rpc/CMakeLists.txt +++ b/tools/rpc/CMakeLists.txt @@ -1,4 +1,4 @@ -set(TARGET rpc-server) +set(TARGET ggml-rpc-server) add_executable(${TARGET} rpc-server.cpp) target_link_libraries(${TARGET} PRIVATE ggml) target_compile_features(${TARGET} PRIVATE cxx_std_17) diff --git a/tools/rpc/README.md b/tools/rpc/README.md index 05b7292c03..655b65347e 100644 --- a/tools/rpc/README.md +++ b/tools/rpc/README.md @@ -4,8 +4,8 @@ > This example and the RPC backend are currently in a proof-of-concept development stage. As such, the functionality is fragile and > insecure. **Never run the RPC server on an open network or in a sensitive environment!** -The `rpc-server` allows exposing `ggml` devices on a remote host. -The RPC backend communicates with one or several instances of `rpc-server` and offloads computations to them. +The `ggml-rpc-server` allows exposing `ggml` devices on a remote host. +The RPC backend communicates with one or several instances of `ggml-rpc-server` and offloads computations to them. This can be used for distributed LLM inference with `llama.cpp` in the following way: ```mermaid @@ -14,15 +14,15 @@ flowchart TD rpcb<-->|TCP|srvb rpcb<-.->|TCP|srvn subgraph hostn[Host N] - srvn[rpc-server]<-.->dev4["CUDA0"] - srvn[rpc-server]<-.->dev5["CPU"] + srvn[ggml-rpc-server]<-.->dev4["CUDA0"] + srvn[ggml-rpc-server]<-.->dev5["CPU"] end subgraph hostb[Host B] - srvb[rpc-server]<-->dev3["Metal"] + srvb[ggml-rpc-server]<-->dev3["Metal"] end subgraph hosta[Host A] - srva[rpc-server]<-->dev["CUDA0"] - srva[rpc-server]<-->dev2["CUDA1"] + srva[ggml-rpc-server]<-->dev["CUDA0"] + srva[ggml-rpc-server]<-->dev2["CUDA1"] end subgraph host[Main Host] local["Local devices"]<-->ggml[llama-cli] @@ -33,7 +33,7 @@ flowchart TD class local,dev,dev2,dev3,dev4,dev5 devcls ``` -By default, `rpc-server` exposes all available accelerator devices on the host. +By default, `ggml-rpc-server` exposes all available accelerator devices on the host. If there are no accelerators, it exposes a single `CPU` device. ## Usage @@ -41,7 +41,7 @@ If there are no accelerators, it exposes a single `CPU` device. ### Remote hosts On each remote host, build the backends for each accelerator by adding `-DGGML_RPC=ON` to the build options. -For example, to build the `rpc-server` with support for CUDA accelerators: +For example, to build the `ggml-rpc-server` with support for CUDA accelerators: ```bash mkdir build-rpc-cuda @@ -50,10 +50,10 @@ cmake .. -DGGML_CUDA=ON -DGGML_RPC=ON cmake --build . --config Release ``` -When started, the `rpc-server` will detect and expose all available `CUDA` devices: +When started, the `ggml-rpc-server` will detect and expose all available `CUDA` devices: ```bash -$ bin/rpc-server +$ bin/ggml-rpc-server ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: @@ -67,14 +67,14 @@ Devices: You can control the set of exposed CUDA devices with the `CUDA_VISIBLE_DEVICES` environment variable or the `--device` command line option. The following two commands have the same effect: ```bash -$ CUDA_VISIBLE_DEVICES=0 bin/rpc-server -p 50052 -$ bin/rpc-server --device CUDA0 -p 50052 +$ CUDA_VISIBLE_DEVICES=0 bin/ggml-rpc-server -p 50052 +$ bin/ggml-rpc-server --device CUDA0 -p 50052 ``` ### Main host On the main host build `llama.cpp` with the backends for the local devices and add `-DGGML_RPC=ON` to the build options. -Finally, when running `llama-cli` or `llama-server`, use the `--rpc` option to specify the host and port of each `rpc-server`: +Finally, when running `llama-cli` or `llama-server`, use the `--rpc` option to specify the host and port of each `ggml-rpc-server`: ```bash $ llama-cli -hf ggml-org/gemma-3-1b-it-GGUF -ngl 99 --rpc 192.168.88.10:50052,192.168.88.11:50052 @@ -90,7 +90,7 @@ This can speed up model loading significantly, especially when using large model To enable the cache, use the `-c` option: ```bash -$ bin/rpc-server -c +$ bin/ggml-rpc-server -c ``` By default, the cache is stored in the `$HOME/.cache/llama.cpp/rpc` directory and can be controlled via the `LLAMA_CACHE` environment variable. @@ -103,8 +103,8 @@ RDMA is enabled by default when `libibverbs` is found at build time. ### Troubleshooting -Use the `GGML_RPC_DEBUG` environment variable to enable debug messages from `rpc-server`: +Use the `GGML_RPC_DEBUG` environment variable to enable debug messages from `ggml-rpc-server`: ```bash -$ GGML_RPC_DEBUG=1 bin/rpc-server +$ GGML_RPC_DEBUG=1 bin/ggml-rpc-server ```