CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

server: update refs -> llama-server

Browse Source 
gitignore llama-server
This commit is contained in:
Olivier Chafik
2024-06-06 15:39:23 +01:00
parent 849842916d
commit f298cc63d2
16 changed files with 35 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.devops/server-cuda.Dockerfile
View File

@@ -25,13 +25,13 @@ ENV LLAMA_CUDA=1
# Enable cURL # Enable cURL
ENV LLAMA_CURL=1 ENV LLAMA_CURL=1
RUN make -j$(nproc) server RUN make -j$(nproc) llama-server
FROM ${BASE_CUDA_RUN_CONTAINER} as runtime FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y libcurl4-openssl-dev libgomp1 apt-get install -y libcurl4-openssl-dev libgomp1
COPY --from=build /app/server /server COPY --from=build /app/llama-server /llama-server
ENTRYPOINT [ "/server" ] ENTRYPOINT [ "/llama-server" ]

4
.devops/server-intel.Dockerfile
View File

@@ -38,8 +38,8 @@ RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRO
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y libcurl4-openssl-dev apt-get install -y libcurl4-openssl-dev
COPY --from=build /app/build/bin/server /server COPY --from=build /app/build/bin/llama-server /llama-server
ENV LC_ALL=C.utf8 ENV LC_ALL=C.utf8
ENTRYPOINT [ "/server" ] ENTRYPOINT [ "/llama-server" ]

4
.devops/server-rocm.Dockerfile
View File

@@ -45,6 +45,6 @@ ENV LLAMA_CURL=1
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y libcurl4-openssl-dev apt-get install -y libcurl4-openssl-dev
RUN make -j$(nproc) RUN make -j$(nproc) llama-server
ENTRYPOINT [ "/app/server" ] ENTRYPOINT [ "/app/llama-server" ]

4
.devops/server-vulkan.Dockerfile
View File

@@ -23,9 +23,9 @@ RUN cmake -B build -DLLAMA_VULKAN=1 -DLLAMA_CURL=1 && \
# Clean up # Clean up
WORKDIR / WORKDIR /
RUN cp /app/build/bin/server /server && \ RUN cp /app/build/bin/llama-server /llama-server && \
rm -rf /app rm -rf /app
ENV LC_ALL=C.utf8 ENV LC_ALL=C.utf8
ENTRYPOINT [ "/server" ] ENTRYPOINT [ "/llama-server" ]

6
.devops/server.Dockerfile
View File

@@ -11,15 +11,15 @@ COPY . .
ENV LLAMA_CURL=1 ENV LLAMA_CURL=1
RUN make -j$(nproc) server RUN make -j$(nproc) llama-server
FROM ubuntu:$UBUNTU_VERSION as runtime FROM ubuntu:$UBUNTU_VERSION as runtime
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y libcurl4-openssl-dev libgomp1 apt-get install -y libcurl4-openssl-dev libgomp1
COPY --from=build /app/server /server COPY --from=build /app/llama-server /llama-server
ENV LC_ALL=C.utf8 ENV LC_ALL=C.utf8
ENTRYPOINT [ "/server" ] ENTRYPOINT [ "/llama-server" ]

2
.devops/tools.sh
View File

@@ -26,7 +26,7 @@ elif [[ "$arg1" == '--all-in-one' || "$arg1" == '-a' ]]; then
fi fi
done done
elif [[ "$arg1" == '--server' || "$arg1" == '-s' ]]; then elif [[ "$arg1" == '--server' || "$arg1" == '-s' ]]; then
./server "$@" ./llama-server "$@"
else else
echo "Unknown command: $arg1" echo "Unknown command: $arg1"
echo "Available commands: " echo "Available commands: "

2
.gitignore vendored
View File

@@ -76,7 +76,7 @@ models-mnt
/quantize-stats /quantize-stats
/result /result
/save-load-state /save-load-state
/server /llama-server
/simple /simple
/batched /batched
/batched-bench /batched-bench

2
examples/json-schema-pydantic-example.py
View File

@@ -1,5 +1,5 @@
# Usage: # Usage:
#! ./server -m some-model.gguf & #! ./llama-server -m some-model.gguf &
#! pip install pydantic #! pip install pydantic
#! python json-schema-pydantic-example.py #! python json-schema-pydantic-example.py

2
examples/server-llama2-13B.sh
View File

@@ -16,7 +16,7 @@ GEN_OPTIONS="${GEN_OPTIONS:---ctx_size 4096 --batch-size 1024}"
# shellcheck disable=SC2086 # Intended splitting of GEN_OPTIONS # shellcheck disable=SC2086 # Intended splitting of GEN_OPTIONS
./server $GEN_OPTIONS \ ./llama-server $GEN_OPTIONS \
--model "$MODEL" \ --model "$MODEL" \
--threads "$N_THREAD" \ --threads "$N_THREAD" \
--rope-freq-scale 1.0 \ --rope-freq-scale 1.0 \

22
examples/server/README.md
View File

@@ -80,26 +80,26 @@ The project is under active development, and we are [looking for feedback and co
## Build ## 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`: - Using `make`:
```bash ```bash
make server make llama-server
``` ```
- Using `CMake`: - Using `CMake`:
```bash ```bash
cmake -B build 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 ## 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`: - 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: # NOTE: For non-system openssl, use the following:
# CXXFLAGS="-I /path/to/openssl/include" # CXXFLAGS="-I /path/to/openssl/include"
# LDFLAGS="-L /path/to/openssl/lib" # LDFLAGS="-L /path/to/openssl/lib"
make LLAMA_SERVER_SSL=true server make LLAMA_SERVER_SSL=true llama-server
``` ```
- Using `CMake`: - Using `CMake`:
```bash ```bash
cmake -B build -DLLAMA_SERVER_SSL=ON cmake -B build -DLLAMA_SERVER_SSL=ON
cmake --build build --config Release -t server cmake --build build --config Release -t llama-server
``` ```
## Quick Start ## 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.) ### Unix-based systems (Linux, macOS, etc.)
```bash ```bash
./server -m models/7B/ggml-model.gguf -c 2048 ./llama-server -m models/7B/ggml-model.gguf -c 2048
``` ```
### Windows ### Windows
```powershell ```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`. 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 ### 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 ### 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: Example of an error:

2
examples/server/bench/README.md
View File

@@ -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: It aims to be used in the CI, but you can run it manually:
```shell ```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 \ --runner-label local \
--name local \ --name local \
--branch `git rev-parse --abbrev-ref HEAD` \ --branch `git rev-parse --abbrev-ref HEAD` \

2
examples/server/bench/bench.py
View File

@@ -245,7 +245,7 @@ def start_server(args):
def start_server_background(args): def start_server_background(args):
# Start the server # Start the server
server_path = '../../../build/bin/server' server_path = '../../../build/bin/llama-server'
if 'LLAMA_SERVER_BIN_PATH' in os.environ: if 'LLAMA_SERVER_BIN_PATH' in os.environ:
server_path = os.environ['LLAMA_SERVER_BIN_PATH'] server_path = os.environ['LLAMA_SERVER_BIN_PATH']
server_args = [ server_args = [

4
examples/server/public_simplechat/readme.md
View File

@@ -44,12 +44,12 @@ http module.
### running using examples/server ### 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 ### running using python3's server module
first run examples/server 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 next run this web front end in examples/server/public_simplechat
* cd ../examples/server/public_simplechat * cd ../examples/server/public_simplechat

2
examples/server/tests/README.md
View File

@@ -40,7 +40,7 @@ It's possible to override some scenario steps values with environment variables:
| variable | description | | variable | description |
|--------------------------|------------------------------------------------------------------------------------------------| |--------------------------|------------------------------------------------------------------------------------------------|
| `PORT` | `context.server_port` to set the listening port of the server during scenario, default: `8080` | | `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` | | `DEBUG` | "ON" to enable steps and server verbose mode `--verbose` |
| `SERVER_LOG_FORMAT_JSON` | if set switch server logs to json format | | `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` | | `N_GPU_LAYERS` | number of model layers to offload to VRAM `-ngl --n-gpu-layers` |

4
examples/server/tests/features/steps/steps.py
View File

@@ -1272,9 +1272,9 @@ def context_text(context):
def start_server_background(context): def start_server_background(context):
if os.name == 'nt': if os.name == 'nt':
context.server_path = '../../../build/bin/Release/server.exe' context.server_path = '../../../build/bin/Release/llama-server.exe'
else: else:
context.server_path = '../../../build/bin/server' context.server_path = '../../../build/bin/llama-server'
if 'LLAMA_SERVER_BIN_PATH' in os.environ: if 'LLAMA_SERVER_BIN_PATH' in os.environ:
context.server_path = os.environ['LLAMA_SERVER_BIN_PATH'] context.server_path = os.environ['LLAMA_SERVER_BIN_PATH']
server_listen_addr = context.server_fqdn server_listen_addr = context.server_fqdn

2
grammars/README.md
View File

@@ -1,6 +1,6 @@
# GBNF Guide # GBNF Guide
GBNF (GGML BNF) is a format for defining [formal grammars](https://en.wikipedia.org/wiki/Formal_grammar) to constrain model outputs in `llama.cpp`. For example, you can use it to force the model to generate valid JSON, or speak only in emojis. GBNF grammars are supported in various ways in `examples/main` and `examples/server`. GBNF (GGML BNF) is a format for defining [formal grammars](https://en.wikipedia.org/wiki/Formal_grammar) to constrain model outputs in `llama.cpp`. For example, you can use it to force the model to generate valid JSON, or speak only in emojis. GBNF grammars are supported in various ways in `examples/main` and `examples/llama-server`.
## Background ## Background