Initial SQL-only 1C adapter baseline
This commit is contained in:
@@ -0,0 +1,38 @@
|
||||
name: llm-transformers-audio
|
||||
|
||||
services:
|
||||
audio-api:
|
||||
image: ${TRANSFORMERS_IMAGE:-vllm/vllm-openai:v0.10.2}
|
||||
container_name: ${TRANSFORMERS_CONTAINER_NAME:-llm-transformers-audio}
|
||||
restart: unless-stopped
|
||||
ipc: host
|
||||
ports:
|
||||
- "${TRANSFORMERS_HOST_PORT:-8020}:8020"
|
||||
environment:
|
||||
HF_HOME: /root/.cache/huggingface
|
||||
MODEL_PATH: ${MODEL_PATH:-/models/audio/whisper-large-v3-turbo}
|
||||
SERVED_MODEL_NAME: ${SERVED_MODEL_NAME:-whisper-large-v3-turbo}
|
||||
PORT: "8020"
|
||||
LOAD_ON_START: ${LOAD_ON_START:-0}
|
||||
volumes:
|
||||
- ${HOST_APP_DIR:-Z:/LLM/model-chat-app}:/app
|
||||
- ${HOST_MODELS_DIR:-Z:/LLM/models}:/models
|
||||
- ${HOST_HF_CACHE_DIR:-Z:/LLM/models/cache/huggingface}:/root/.cache/huggingface
|
||||
working_dir: /app
|
||||
entrypoint: python3
|
||||
command:
|
||||
- scripts/transformers_plugin_server.py
|
||||
- --plugin
|
||||
- audio
|
||||
- --host
|
||||
- 0.0.0.0
|
||||
- --port
|
||||
- "8020"
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
devices:
|
||||
- driver: nvidia
|
||||
count: all
|
||||
capabilities:
|
||||
- gpu
|
||||
@@ -0,0 +1,9 @@
|
||||
HOST_APP_DIR=Z:/LLM/model-chat-app
|
||||
HOST_MODELS_DIR=Z:/LLM/models
|
||||
HOST_HF_CACHE_DIR=Z:/LLM/models/cache/huggingface
|
||||
TRANSFORMERS_IMAGE=vllm/vllm-openai:v0.10.2
|
||||
TRANSFORMERS_CONTAINER_NAME=llm-transformers-audio
|
||||
TRANSFORMERS_HOST_PORT=8020
|
||||
MODEL_PATH=/models/audio/whisper-large-v3-turbo
|
||||
SERVED_MODEL_NAME=whisper-large-v3-turbo
|
||||
LOAD_ON_START=0
|
||||
@@ -0,0 +1,10 @@
|
||||
FROM vllm/vllm-openai:v0.10.2
|
||||
|
||||
RUN python3 -m pip install --no-cache-dir \
|
||||
"diffusers>=0.35.0" \
|
||||
"transformers>=4.51.0" \
|
||||
"accelerate>=1.0.0" \
|
||||
safetensors \
|
||||
pillow
|
||||
|
||||
WORKDIR /app
|
||||
@@ -0,0 +1,42 @@
|
||||
name: llm-transformers-image
|
||||
|
||||
services:
|
||||
image-api:
|
||||
image: ${TRANSFORMERS_IMAGE:-llm-transformers-image:latest}
|
||||
build:
|
||||
context: ../../../../
|
||||
dockerfile: core/deploy/docker-gpu/transformers/image.Dockerfile
|
||||
container_name: ${TRANSFORMERS_CONTAINER_NAME:-llm-transformers-image}
|
||||
restart: unless-stopped
|
||||
ipc: host
|
||||
ports:
|
||||
- "${TRANSFORMERS_HOST_PORT:-8040}:8040"
|
||||
environment:
|
||||
HF_HOME: /root/.cache/huggingface
|
||||
MODEL_PATH: ${MODEL_PATH:-/models/image/sdxl-base-1.0}
|
||||
EDIT_MODEL_PATH: ${EDIT_MODEL_PATH:-/models/image/sdxl-inpainting-1.0}
|
||||
SERVED_MODEL_NAME: ${SERVED_MODEL_NAME:-sdxl-image}
|
||||
PORT: "8040"
|
||||
LOAD_ON_START: ${LOAD_ON_START:-1}
|
||||
BACKGROUND_LOAD_ON_START: ${BACKGROUND_LOAD_ON_START:-1}
|
||||
volumes:
|
||||
- ${HOST_APP_DIR:-Z:/LLM/model-chat-app}:/app
|
||||
- ${HOST_MODELS_DIR:-Z:/LLM/models}:/models
|
||||
- ${HOST_HF_CACHE_DIR:-Z:/LLM/models/cache/huggingface}:/root/.cache/huggingface
|
||||
working_dir: /app
|
||||
entrypoint: /bin/sh
|
||||
command:
|
||||
- -lc
|
||||
- >
|
||||
exec python3 scripts/transformers_plugin_server.py
|
||||
--plugin image
|
||||
--host 0.0.0.0
|
||||
--port 8040
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
devices:
|
||||
- driver: nvidia
|
||||
count: all
|
||||
capabilities:
|
||||
- gpu
|
||||
@@ -0,0 +1,11 @@
|
||||
HOST_APP_DIR=Z:/LLM/model-chat-app
|
||||
HOST_MODELS_DIR=Z:/LLM/models
|
||||
HOST_HF_CACHE_DIR=Z:/LLM/models/cache/huggingface
|
||||
TRANSFORMERS_IMAGE=llm-transformers-image:latest
|
||||
TRANSFORMERS_CONTAINER_NAME=llm-transformers-image
|
||||
TRANSFORMERS_HOST_PORT=8040
|
||||
MODEL_PATH=/models/image/sdxl-base-1.0
|
||||
EDIT_MODEL_PATH=/models/image/sdxl-inpainting-1.0
|
||||
SERVED_MODEL_NAME=sdxl-image
|
||||
LOAD_ON_START=1
|
||||
BACKGROUND_LOAD_ON_START=1
|
||||
@@ -0,0 +1,11 @@
|
||||
HOST_APP_DIR=Z:/LLM/model-chat-app
|
||||
HOST_MODELS_DIR=Z:/LLM/models
|
||||
HOST_HF_CACHE_DIR=Z:/LLM/models/cache/huggingface
|
||||
TRANSFORMERS_IMAGE=llm-transformers-image:latest
|
||||
TRANSFORMERS_CONTAINER_NAME=llm-transformers-image
|
||||
TRANSFORMERS_HOST_PORT=8040
|
||||
MODEL_PATH=/models/image/qwen-image-edit
|
||||
EDIT_MODEL_PATH=/models/image/qwen-image-edit
|
||||
SERVED_MODEL_NAME=qwen-image-edit
|
||||
LOAD_ON_START=0
|
||||
BACKGROUND_LOAD_ON_START=0
|
||||
@@ -0,0 +1,38 @@
|
||||
name: llm-transformers-translation
|
||||
|
||||
services:
|
||||
translation-api:
|
||||
image: ${TRANSFORMERS_IMAGE:-vllm/vllm-openai:v0.10.2}
|
||||
container_name: ${TRANSFORMERS_CONTAINER_NAME:-llm-transformers-translation}
|
||||
restart: unless-stopped
|
||||
ipc: host
|
||||
ports:
|
||||
- "${TRANSFORMERS_HOST_PORT:-8010}:8010"
|
||||
environment:
|
||||
HF_HOME: /root/.cache/huggingface
|
||||
MODEL_PATH: ${MODEL_PATH:-/models/translation/lmt-60-4b}
|
||||
SERVED_MODEL_NAME: ${SERVED_MODEL_NAME:-lmt-60-4b}
|
||||
PORT: "8010"
|
||||
LOAD_ON_START: ${LOAD_ON_START:-0}
|
||||
volumes:
|
||||
- ${HOST_APP_DIR:-Z:/LLM/model-chat-app}:/app
|
||||
- ${HOST_MODELS_DIR:-Z:/LLM/models}:/models
|
||||
- ${HOST_HF_CACHE_DIR:-Z:/LLM/models/cache/huggingface}:/root/.cache/huggingface
|
||||
working_dir: /app
|
||||
entrypoint: python3
|
||||
command:
|
||||
- scripts/transformers_plugin_server.py
|
||||
- --plugin
|
||||
- translation
|
||||
- --host
|
||||
- 0.0.0.0
|
||||
- --port
|
||||
- "8010"
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
devices:
|
||||
- driver: nvidia
|
||||
count: all
|
||||
capabilities:
|
||||
- gpu
|
||||
@@ -0,0 +1,9 @@
|
||||
HOST_APP_DIR=Z:/LLM/model-chat-app
|
||||
HOST_MODELS_DIR=Z:/LLM/models
|
||||
HOST_HF_CACHE_DIR=Z:/LLM/models/cache/huggingface
|
||||
TRANSFORMERS_IMAGE=vllm/vllm-openai:v0.10.2
|
||||
TRANSFORMERS_CONTAINER_NAME=llm-transformers-translation
|
||||
TRANSFORMERS_HOST_PORT=8010
|
||||
MODEL_PATH=/models/translation/lmt-60-4b
|
||||
SERVED_MODEL_NAME=lmt-60-4b
|
||||
LOAD_ON_START=0
|
||||
@@ -0,0 +1,38 @@
|
||||
name: llm-transformers-video
|
||||
|
||||
services:
|
||||
video-api:
|
||||
image: ${TRANSFORMERS_IMAGE:-vllm/vllm-openai:v0.10.2}
|
||||
container_name: ${TRANSFORMERS_CONTAINER_NAME:-llm-transformers-video}
|
||||
restart: unless-stopped
|
||||
ipc: host
|
||||
ports:
|
||||
- "${TRANSFORMERS_HOST_PORT:-8030}:8030"
|
||||
environment:
|
||||
HF_HOME: /root/.cache/huggingface
|
||||
MODEL_PATH: ${MODEL_PATH:-/models/video/qwen2.5-vl-7b-instruct}
|
||||
SERVED_MODEL_NAME: ${SERVED_MODEL_NAME:-qwen2.5-vl-7b-instruct}
|
||||
PORT: "8030"
|
||||
LOAD_ON_START: ${LOAD_ON_START:-0}
|
||||
volumes:
|
||||
- ${HOST_APP_DIR:-Z:/LLM/model-chat-app}:/app
|
||||
- ${HOST_MODELS_DIR:-Z:/LLM/models}:/models
|
||||
- ${HOST_HF_CACHE_DIR:-Z:/LLM/models/cache/huggingface}:/root/.cache/huggingface
|
||||
working_dir: /app
|
||||
entrypoint: python3
|
||||
command:
|
||||
- scripts/transformers_plugin_server.py
|
||||
- --plugin
|
||||
- video
|
||||
- --host
|
||||
- 0.0.0.0
|
||||
- --port
|
||||
- "8030"
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
devices:
|
||||
- driver: nvidia
|
||||
count: all
|
||||
capabilities:
|
||||
- gpu
|
||||
@@ -0,0 +1,9 @@
|
||||
HOST_APP_DIR=Z:/LLM/model-chat-app
|
||||
HOST_MODELS_DIR=Z:/LLM/models
|
||||
HOST_HF_CACHE_DIR=Z:/LLM/models/cache/huggingface
|
||||
TRANSFORMERS_IMAGE=vllm/vllm-openai:v0.10.2
|
||||
TRANSFORMERS_CONTAINER_NAME=llm-transformers-video
|
||||
TRANSFORMERS_HOST_PORT=8030
|
||||
MODEL_PATH=/models/video/qwen2.5-vl-7b-instruct
|
||||
SERVED_MODEL_NAME=qwen2.5-vl-7b-instruct
|
||||
LOAD_ON_START=0
|
||||
Reference in New Issue
Block a user