diff --git a/send_local_request_to_cogvlm.py b/send_local_request_to_cogvlm.py index e99b0ac..2139c3e 100644 --- a/send_local_request_to_cogvlm.py +++ b/send_local_request_to_cogvlm.py @@ -55,7 +55,7 @@ def image_to_base64(image_path): start_time = time.time() # Send the request -response = requests.post(url, json=request_data) # headers=headers) +response = requests.post(url, json=request_data) # headers=headers) # Stop the timer end_time = time.time() diff --git a/servers/cogvlm/cogvlm.py b/servers/cogvlm/cogvlm.py index aac3e7f..bb66a1f 100644 --- a/servers/cogvlm/cogvlm.py +++ b/servers/cogvlm/cogvlm.py @@ -34,6 +34,7 @@ TextContent, UsageInfo, ) + # from exa.structs.parallelize_models_gpus import prepare_model_for_ddp_inference # Load environment variables from .env file @@ -110,7 +111,7 @@ async def list_models(): @app.post("/v1/chat/completions", response_model=ChatCompletionResponse) async def create_chat_completion( - request: ChatCompletionRequest, # token: str = Depends(authenticate_user) + request: ChatCompletionRequest, # token: str = Depends(authenticate_user) ): try: if len(request.messages) < 1 or request.messages[-1].role == "assistant":