apps/photoprism
1
0
Fork 0
mirror of https://github.com/photoprism/photoprism.git synced 2025-09-27 05:08:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

Setup: Update Ollama service examples in compose.alldbms.yaml file

Browse Source
This commit is contained in:
Keith Martin
2025-09-02 11:15:57 +10:00
parent ed62352090
commit 7856e0ceb8
1 changed files with 16 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
compose.alldbms.yaml
View File

@@ -273,21 +273,22 @@ services:
environment:
## Ollama Configuration Options:
OLLAMA_HOST: "0.0.0.0:11434"
OLLAMA_MODELS: "/root/.ollama" # model storage path (see volumes section below)
OLLAMA_MAX_QUEUE: "100" # maximum number of queued requests
OLLAMA_NUM_PARALLEL: "1" # maximum number of parallel requests
OLLAMA_MAX_LOADED_MODELS: "1" # maximum number of loaded models per GPU
OLLAMA_LOAD_TIMEOUT: "5m" # maximum time for loading models (default "5m")
OLLAMA_KEEP_ALIVE: "10m" # duration that models stay loaded in memory (default "5m")
OLLAMA_CONTEXT_LENGTH: "4096" # maximum input context length
OLLAMA_MULTIUSER_CACHE: "1" # optimize prompt caching for multi-user scenarios
# OLLAMA_DEBUG: "1" # shows additional debug information
# OLLAMA_NOPRUNE: "1" # disables pruning of model blobs at startup
# OLLAMA_NOHISTORY: "1" # disables readline history
# OLLAMA_FLASH_ATTENTION: "1" # enables the experimental flash attention feature
# OLLAMA_SCHED_SPREAD: "1" # allows scheduling models across all GPUs.
# OLLAMA_GPU_OVERHEAD: "0" # reserves a portion of VRAM per GPU (bytes)
# OLLAMA_INTEL_GPU: "1" # enables experimental Intel GPU detection
OLLAMA_MODELS: "/root/.ollama" # model storage path (see volumes section below)
OLLAMA_MAX_QUEUE: "100" # maximum number of queued requests
OLLAMA_NUM_PARALLEL: "1" # maximum number of parallel requests
OLLAMA_MAX_LOADED_MODELS: "1" # maximum number of loaded models per GPU
OLLAMA_LOAD_TIMEOUT: "5m" # maximum time for loading models (default "5m")
OLLAMA_KEEP_ALIVE: "5m" # duration that models stay loaded in memory (default "5m")
OLLAMA_CONTEXT_LENGTH: "4096" # maximum input context length
OLLAMA_MULTIUSER_CACHE: "false" # optimize prompt caching for multi-user scenarios
OLLAMA_NOPRUNE: "false" # disables pruning of model blobs at startup
OLLAMA_NOHISTORY: "true" # disables readline history
OLLAMA_FLASH_ATTENTION: "false" # enables the experimental flash attention feature
OLLAMA_KV_CACHE_TYPE: "f16" # cache quantization (f16, q8_0, or q4_0)
OLLAMA_SCHED_SPREAD: "false" # allows scheduling models across all GPUs.
OLLAMA_NEW_ENGINE: "true" # enables the new Ollama engine
# OLLAMA_DEBUG: "true" # shows additional debug information
# OLLAMA_INTEL_GPU: "true" # enables experimental Intel GPU detection
## NVIDIA GPU Hardware Acceleration (optional):
# NVIDIA_VISIBLE_DEVICES: "all"
# NVIDIA_DRIVER_CAPABILITIES: "compute,utility"