Model: Add proper jobs cleanup and fix var calls

Jobs should be started and immediately cleaned up when calling the
generation stream. Expose a stream_generate function and append
this to the base class since it's more idiomatic than generate_gen.

The exl2 container's generate_gen function is now internal.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>

endpoints/Kobold/utils/generation.py

@@ -52,7 +52,7 @@ async def _stream_collector(data: GenerateRequest, request: Request):
     try:
         logger.info(f"Received Kobold generation request {data.genkey}")
 
-        generator = model.container.generate_gen(
+        generator = model.container.stream_generate(
             request_id=data.genkey, abort_event=abort_event, **data.model_dump()
         )
         async for generation in generator:

endpoints/OAI/utils/completion.py

@@ -95,7 +95,7 @@ async def _stream_collector(
     """Collects a stream and places results in a common queue"""
 
     try:
-        new_generation = model.container.generate_gen(
+        new_generation = model.container.stream_generate(
             request_id,
             prompt,
             params,
@@ -120,7 +120,7 @@ async def load_inline_model(model_name: str, request: Request):
     if (
         model.container
         and model.container.model_dir.name == model_name
-        and model.container.model_loaded
+        and model.container.loaded
     ):
         return