fix(autogptq): do not use_triton with qwen-vl (#1985)

* Enhance autogptq backend to support VL models

* update dependencies for autogptq

* remove redundant auto-gptq dependency

* Convert base64 to image_url for Qwen-VL model

* implemented model inference for qwen-vl

* remove user prompt from generated answer

* fixed write image error

* fixed use_triton issue when loading Qwen-VL model

---------

Co-authored-by: Binghua Wu <[email protected]>

backend/python/autogptq/autogptq.py

@@ -39,7 +39,6 @@ def LoadModel(self, request, context):
  self.model_name = "Qwen-VL-Chat"
  model = AutoModelForCausalLM.from_pretrained(model_path, 
  trust_remote_code=request.TrustRemoteCode,
- use_triton=request.UseTriton,
  device_map="auto").eval()
  else:
  model = AutoGPTQForCausalLM.from_quantized(model_path,