3 parallel models
This commit is contained in:
@@ -31,7 +31,7 @@ in
|
||||
FLASH_ATTENTION = "1";
|
||||
OLLAMA_KV_CACHE_TYPE = "q8_0";
|
||||
# Ollama memory configuration
|
||||
OLLAMA_MAX_LOADED_MODELS = "2";
|
||||
OLLAMA_MAX_LOADED_MODELS = "3";
|
||||
OLLAMA_MAX_QUEUE = "512";
|
||||
OLLAMA_NUM_PARALLEL = "1";
|
||||
|
||||
|
||||
Reference in New Issue
Block a user