diff options
Diffstat (limited to 'examples/server')
| -rw-r--r-- | examples/server/CMakeLists.txt | 2 | ||||
| -rw-r--r-- | examples/server/README.md | 22 | ||||
| -rw-r--r-- | examples/server/bench/README.md | 2 | ||||
| -rw-r--r-- | examples/server/bench/bench.py | 2 | ||||
| -rw-r--r-- | examples/server/public_simplechat/readme.md | 4 | ||||
| -rw-r--r-- | examples/server/tests/README.md | 8 | ||||
| -rw-r--r-- | examples/server/tests/features/steps/steps.py | 4 |
7 files changed, 21 insertions, 23 deletions
diff --git a/examples/server/CMakeLists.txt b/examples/server/CMakeLists.txt index dab70961..8365f951 100644 --- a/examples/server/CMakeLists.txt +++ b/examples/server/CMakeLists.txt @@ -1,4 +1,4 @@ -set(TARGET server) +set(TARGET llama-server) option(LLAMA_SERVER_VERBOSE "Build verbose logging option for Server" ON) option(LLAMA_SERVER_SSL "Build SSL support for the server" OFF) include_directories(${CMAKE_CURRENT_SOURCE_DIR} ${CMAKE_CURRENT_BINARY_DIR}) diff --git a/examples/server/README.md b/examples/server/README.md index ccbdcdbd..e7fb0bf6 100644 --- a/examples/server/README.md +++ b/examples/server/README.md @@ -80,26 +80,26 @@ The project is under active development, and we are [looking for feedback and co ## Build -`server` is built alongside everything else from the root of the project +`llama-server` is built alongside everything else from the root of the project - Using `make`: ```bash - make server + make llama-server ``` - Using `CMake`: ```bash cmake -B build - cmake --build build --config Release -t server + cmake --build build --config Release -t llama-server ``` - Binary is at `./build/bin/server` + Binary is at `./build/bin/llama-server` ## Build with SSL -`server` can also be built with SSL support using OpenSSL 3 +`llama-server` can also be built with SSL support using OpenSSL 3 - Using `make`: @@ -107,14 +107,14 @@ The project is under active development, and we are [looking for feedback and co # NOTE: For non-system openssl, use the following: # CXXFLAGS="-I /path/to/openssl/include" # LDFLAGS="-L /path/to/openssl/lib" - make LLAMA_SERVER_SSL=true server + make LLAMA_SERVER_SSL=true llama-server ``` - Using `CMake`: ```bash cmake -B build -DLLAMA_SERVER_SSL=ON - cmake --build build --config Release -t server + cmake --build build --config Release -t llama-server ``` ## Quick Start @@ -124,13 +124,13 @@ To get started right away, run the following command, making sure to use the cor ### Unix-based systems (Linux, macOS, etc.) ```bash -./server -m models/7B/ggml-model.gguf -c 2048 +./llama-server -m models/7B/ggml-model.gguf -c 2048 ``` ### Windows ```powershell -server.exe -m models\7B\ggml-model.gguf -c 2048 +llama-server.exe -m models\7B\ggml-model.gguf -c 2048 ``` The above command will start a server that by default listens on `127.0.0.1:8080`. @@ -629,11 +629,11 @@ bash chat.sh ### OAI-like API -The HTTP `server` supports an OAI-like API: https://github.com/openai/openai-openapi +The HTTP `llama-server` supports an OAI-like API: https://github.com/openai/openai-openapi ### API errors -`server` returns errors in the same format as OAI: https://github.com/openai/openai-openapi +`llama-server` returns errors in the same format as OAI: https://github.com/openai/openai-openapi Example of an error: diff --git a/examples/server/bench/README.md b/examples/server/bench/README.md index 23a3ec97..0f18ca39 100644 --- a/examples/server/bench/README.md +++ b/examples/server/bench/README.md @@ -99,7 +99,7 @@ The `bench.py` script does several steps: It aims to be used in the CI, but you can run it manually: ```shell -LLAMA_SERVER_BIN_PATH=../../../cmake-build-release/bin/server python bench.py \ +LLAMA_SERVER_BIN_PATH=../../../cmake-build-release/bin/llama-server python bench.py \ --runner-label local \ --name local \ --branch `git rev-parse --abbrev-ref HEAD` \ diff --git a/examples/server/bench/bench.py b/examples/server/bench/bench.py index 86c5de10..4fbbb203 100644 --- a/examples/server/bench/bench.py +++ b/examples/server/bench/bench.py @@ -245,7 +245,7 @@ def start_server(args): def start_server_background(args): # Start the server - server_path = '../../../build/bin/server' + server_path = '../../../build/bin/llama-server' if 'LLAMA_SERVER_BIN_PATH' in os.environ: server_path = os.environ['LLAMA_SERVER_BIN_PATH'] server_args = [ diff --git a/examples/server/public_simplechat/readme.md b/examples/server/public_simplechat/readme.md index 36a46885..2dc17782 100644 --- a/examples/server/public_simplechat/readme.md +++ b/examples/server/public_simplechat/readme.md @@ -44,12 +44,12 @@ http module. ### running using examples/server -bin/server -m path/model.gguf --path ../examples/server/public_simplechat [--port PORT] +./llama-server -m path/model.gguf --path examples/server/public_simplechat [--port PORT] ### running using python3's server module first run examples/server -* bin/server -m path/model.gguf +* ./llama-server -m path/model.gguf next run this web front end in examples/server/public_simplechat * cd ../examples/server/public_simplechat diff --git a/examples/server/tests/README.md b/examples/server/tests/README.md index 83c0208f..5e6cb277 100644 --- a/examples/server/tests/README.md +++ b/examples/server/tests/README.md @@ -27,10 +27,8 @@ To mitigate it, you can increase values in `n_predict`, `kv_size`. ```shell cd ../../.. -mkdir build -cd build -cmake -DLLAMA_CURL=ON ../ -cmake --build . --target server +cmake -B build -DLLAMA_CURL=ON +cmake --build build --target llama-server ``` 2. Start the test: `./tests.sh` @@ -40,7 +38,7 @@ It's possible to override some scenario steps values with environment variables: | variable | description | |--------------------------|------------------------------------------------------------------------------------------------| | `PORT` | `context.server_port` to set the listening port of the server during scenario, default: `8080` | -| `LLAMA_SERVER_BIN_PATH` | to change the server binary path, default: `../../../build/bin/server` | +| `LLAMA_SERVER_BIN_PATH` | to change the server binary path, default: `../../../build/bin/llama-server` | | `DEBUG` | "ON" to enable steps and server verbose mode `--verbose` | | `SERVER_LOG_FORMAT_JSON` | if set switch server logs to json format | | `N_GPU_LAYERS` | number of model layers to offload to VRAM `-ngl --n-gpu-layers` | diff --git a/examples/server/tests/features/steps/steps.py b/examples/server/tests/features/steps/steps.py index 26d9359d..7b5dabb0 100644 --- a/examples/server/tests/features/steps/steps.py +++ b/examples/server/tests/features/steps/steps.py @@ -1272,9 +1272,9 @@ def context_text(context): def start_server_background(context): if os.name == 'nt': - context.server_path = '../../../build/bin/Release/server.exe' + context.server_path = '../../../build/bin/Release/llama-server.exe' else: - context.server_path = '../../../build/bin/server' + context.server_path = '../../../build/bin/llama-server' if 'LLAMA_SERVER_BIN_PATH' in os.environ: context.server_path = os.environ['LLAMA_SERVER_BIN_PATH'] server_listen_addr = context.server_fqdn |