jketreno/backstory
1
0
Fork 0
Code Issues 12 Actions Releases Activity

Remove ollama from being managed by backstory

Browse Source
This commit is contained in:
James Ketr 2025-08-05 17:18:33 -07:00
parent 234148f046
commit f725f35af7
1 changed files with 2 additions and 102 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

104
docker-compose.yml
View File

@ -20,7 +20,7 @@ services:
# - MODEL_NAME=claude-3-5-haiku-latest
- DEFAULT_LLM_PROVIDER=ollama
- MODEL_NAME=${MODEL_NAME:-qwen2.5:7b}
- OLLAMA_HOST=http://ollama:11434
- OLLAMA_HOST=http://battle-linux.ketrenos.com:11434
# Test with OpenVINO; it doesn't work though
# - MODEL_NAME=Qwen3-4B-int4-ov:v1
# - OLLAMA_HOST=http://ollama-ov-server:11434
@ -28,7 +28,6 @@ services:
devices:
- /dev/dri:/dev/dri
depends_on:
- ollama
- redis
networks:
- internal
@ -66,11 +65,10 @@ services:
- SSL_ENABLED=false
- DEFAULT_LLM_PROVIDER=ollama
- MODEL_NAME=${MODEL_NAME:-qwen2.5:7b}
- OLLAMA_HOST=http://ollama:11434
- OLLAMA_HOST=http://battle-linux.ketrenos.com:11434
devices:
- /dev/dri:/dev/dri
depends_on:
- ollama
- redis
networks:
- internal
@ -138,103 +136,6 @@ services:
networks:
- internal
# This doesn't work...
# ollama-intel:
# image: intelanalytics/ipex-llm-inference-cpp-xpu:latest
# container_name: ollama-intel
# restart: unless-stopped
# env_file:
# - .env
# devices:
# - /dev/dri:/dev/dri
# volumes:
# - ./cache:/root/.cache # Cache hub models and neo_compiler_cache
# - ./ollama:/root/.ollama # Cache the ollama models
# ports:
# - 11434:11434
# environment:
# - OLLAMA_HOST=0.0.0.0
# - DEVICE=Arc
# - OLLAMA_INTEL_GPU=true
# - OLLAMA_NUM_GPU=999
# - ZES_ENABLE_SYSMAN=1
# - ONEAPI_DEVICE_SELECTOR=level_zero:0
# - TZ=America/Los_Angeles
# command: sh -c 'mkdir -p /llm/ollama && cd /llm/ollama && init-ollama && exec ./ollama serve'
ollama:
build:
context: .
dockerfile: Dockerfile
target: ollama
container_name: ollama
restart: "always"
env_file:
- .env
environment:
- OLLAMA_HOST=0.0.0.0
- ONEAPI_DEVICE_SELECTOR=level_zero:0
devices:
- /dev/dri:/dev/dri
ports:
- 11434:11434 # ollama serve port
networks:
- internal
volumes:
- ./cache:/root/.cache # Cache hub models and neo_compiler_cache
- ./ollama:/root/.ollama # Cache the ollama models
cap_add: # used for running ze-monitor within container
- CAP_DAC_READ_SEARCH # Bypass all filesystem read access checks
- CAP_PERFMON # Access to perf_events (vs. overloaded CAP_SYS_ADMIN)
- CAP_SYS_PTRACE # PTRACE_MODE_READ_REALCREDS ptrace access mode check
# ollama-ov-server:
# build:
# context: .
# dockerfile: Dockerfile
# target: ollama-ov-server
# container_name: ollama-ov-server
# restart: "no"
# env_file:
# - .env
# environment:
# - OLLAMA_HOST=0.0.0.0
# - ONEAPI_DEVICE_SELECTOR=level_zero:0
# devices:
# - /dev/dri:/dev/dri
# ports:
# - 11435:11434 # ollama serve port
# networks:
# - internal
# volumes:
# - ./cache:/root/.cache # Cache hub models and neo_compiler_cache
# - ./ollama:/root/.ollama # Cache the ollama models
vllm:
build:
context: .
dockerfile: Dockerfile.xpu
target: vllm-openai
container_name: vllm-openai
restart: "always"
shm_size: 10.24gb
env_file:
- .env
environment:
- OLLAMA_HOST=0.0.0.0
# - ONEAPI_DEVICE_SELECTOR=level_zero:0
devices:
- /dev:/dev
- /sys:/sys
ports:
- 11438:8000 # ollama serve port
networks:
- internal
volumes:
- ./cache:/root/.cache # Cache hub models and neo_compiler_cache
- ./ollama:/root/.ollama # Cache the ollama models
privileged: true
jupyter:
build:
context: .
@ -248,7 +149,6 @@ services:
devices:
- /dev/dri:/dev/dri
depends_on:
- ollama
- miniircd
ports:
- 8888:8888 # Jupyter Notebook