Method do_GET

tinygrad/llm/cli.py:113–115

(self)

  server: LLMServer
  def log_request(self, code='-', size='-'): pass
  def do_GET(self):
    if self.path == "/v1/models": self.send_data(json.dumps({"object":"list","data":[{"id":self.server.model_name,"object":"model"}]}).encode())
    else: self.send_data((pathlib.Path(__file__).parent / "chat.html").read_bytes(), content_type="text/html")
  def run_model(self, ids:list[int], model_name:str, include_usage=False, max_tokens:int|None=None, temperature:float=0.0):
    model, tok = self.server.model, self.server.tok
    cache_start_pos = model.get_start_pos(ids)