alexsun/compose-anything
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

style: lint code

Browse Source
This commit is contained in:
Sun-ZhenXing
2026-02-23 17:41:05 +08:00
parent ced072de66
commit 7e14b01b78
240 changed files with 4301 additions and 1539 deletions
Download Patch File Download Diff File Expand all files Collapse all files

127
src/llama.cpp/docker-compose.yaml
View File

@@ -8,7 +8,7 @@ x-defaults: &defaults
driver: json-file
options:
max-size: 100m
max-file: "3"
max-file: '3'
services:
# llama.cpp server - OpenAI-compatible API server
@@ -17,32 +17,31 @@ services:
<<: *defaults
image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:${LLAMA_CPP_SERVER_VARIANT:-server}
ports:
- "${LLAMA_CPP_SERVER_PORT_OVERRIDE:-8080}:8080"
- '${LLAMA_CPP_SERVER_PORT_OVERRIDE:-8080}:8080'
volumes:
- llama_cpp_models:/models
command:
- "-m"
- "${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}"
- "--port"
- "8080"
- "--host"
- "0.0.0.0"
- "-n"
- "${LLAMA_CPP_CONTEXT_SIZE:-512}"
- "--n-gpu-layers"
- "${LLAMA_CPP_GPU_LAYERS:-0}"
- -m
- '${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}'
- --port
- '8080'
- --host
- 0.0.0.0
- -n
- '${LLAMA_CPP_CONTEXT_SIZE:-512}'
- --n-gpu-layers
- '${LLAMA_CPP_GPU_LAYERS:-0}'
environment:
- TZ=${TZ:-UTC}
healthcheck:
test:
[
"CMD",
"wget",
"--quiet",
"--tries=1",
"--spider",
"http://localhost:8080/health",
]
- CMD
- wget
- --quiet
- --tries=1
- --spider
- 'http://localhost:8080/health'
interval: 30s
timeout: 10s
retries: 3
@@ -63,32 +62,31 @@ services:
<<: *defaults
image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:server-cuda
ports:
- "${LLAMA_CPP_SERVER_PORT_OVERRIDE:-8080}:8080"
- '${LLAMA_CPP_SERVER_PORT_OVERRIDE:-8080}:8080'
volumes:
- llama_cpp_models:/models
command:
- "-m"
- "${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}"
- "--port"
- "8080"
- "--host"
- "0.0.0.0"
- "-n"
- "${LLAMA_CPP_CONTEXT_SIZE:-512}"
- "--n-gpu-layers"
- "${LLAMA_CPP_GPU_LAYERS:-99}"
- -m
- '${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}'
- --port
- '8080'
- --host
- 0.0.0.0
- -n
- '${LLAMA_CPP_CONTEXT_SIZE:-512}'
- --n-gpu-layers
- '${LLAMA_CPP_GPU_LAYERS:-99}'
environment:
- TZ=${TZ:-UTC}
healthcheck:
test:
[
"CMD",
"wget",
"--quiet",
"--tries=1",
"--spider",
"http://localhost:8080/health",
]
- CMD
- wget
- --quiet
- --tries=1
- --spider
- 'http://localhost:8080/health'
interval: 30s
timeout: 10s
retries: 3
@@ -114,35 +112,34 @@ services:
<<: *defaults
image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:server-rocm
ports:
- "${LLAMA_CPP_SERVER_PORT_OVERRIDE:-8080}:8080"
- '${LLAMA_CPP_SERVER_PORT_OVERRIDE:-8080}:8080'
volumes:
- llama_cpp_models:/models
devices:
- /dev/kfd
- /dev/dri
command:
- "-m"
- "${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}"
- "--port"
- "8080"
- "--host"
- "0.0.0.0"
- "-n"
- "${LLAMA_CPP_CONTEXT_SIZE:-512}"
- "--n-gpu-layers"
- "${LLAMA_CPP_GPU_LAYERS:-99}"
- -m
- '${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}'
- --port
- '8080'
- --host
- 0.0.0.0
- -n
- '${LLAMA_CPP_CONTEXT_SIZE:-512}'
- --n-gpu-layers
- '${LLAMA_CPP_GPU_LAYERS:-99}'
environment:
- TZ=${TZ:-UTC}
healthcheck:
test:
[
"CMD",
"wget",
"--quiet",
"--tries=1",
"--spider",
"http://localhost:8080/health",
]
- CMD
- wget
- --quiet
- --tries=1
- --spider
- 'http://localhost:8080/health'
interval: 30s
timeout: 10s
retries: 3
@@ -167,12 +164,12 @@ services:
- llama_cpp_models:/models
entrypoint: /app/llama-cli
command:
- "-m"
- "${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}"
- "-p"
- "${LLAMA_CPP_PROMPT:-Hello, how are you?}"
- "-n"
- "${LLAMA_CPP_CONTEXT_SIZE:-512}"
- -m
- '${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}'
- -p
- '${LLAMA_CPP_PROMPT:-Hello, how are you?}'
- -n
- '${LLAMA_CPP_CONTEXT_SIZE:-512}'
environment:
- TZ=${TZ:-UTC}
deploy:
@@ -192,7 +189,7 @@ services:
image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:${LLAMA_CPP_FULL_VARIANT:-full}
volumes:
- llama_cpp_models:/models
command: ["sleep", "infinity"]
command: [sleep, infinity]
environment:
- TZ=${TZ:-UTC}
deploy: