OAI: Add fasttensors to model load endpoint

Also fix logging when loading prompt templates.

Signed-off-by: kingbri <bdashore3@proton.me>

OAI/types/model.py

@@ -90,6 +90,7 @@ class ModelLoadRequest(BaseModel):
     prompt_template: Optional[str] = None
     num_experts_per_token: Optional[int] = None
     use_cfg: Optional[bool] = None
+    fasttensors: Optional[bool] = False
     draft: Optional[DraftModelLoadRequest] = None
 
 

backends/exllamav2/model.py

@@ -243,7 +243,7 @@ class ExllamaV2Container:
     def find_prompt_template(self, prompt_template_name, model_directory):
         """Tries to find a prompt template using various methods"""
 
-        logger.info("Loading prompt template with name " f"{prompt_template_name}")
+        logger.info("Attempting to load a prompt template if present.")
 
         find_template_functions = [
             lambda: get_template_from_model_json(