cdawg

Hey @server-izetov. Thank you for your question, and sorry for the late response. This seems to be true and line 128 ` self.window = np.concatenate([self.window, [input_value]]) ` should be after...

I agree with @geekloper. Thats also how i configured it. However, i looked up the current ModelDescription-Schema but i think the "engine", "apiVersion" and "apiType" may missing. If i follow...

+1 Happing with: - gaunernst/gemma-3-27b-it-int4-awq - cognitivecomputations/DeepSeek-V3-0324-AWQ This almost renders the inference server useless.

Any updates on this? Since this seems to affect both a lot of models and a lot of users.

I believe this feature is quite important, since it gives the freedom to also choose custom models which might be internal and adhere to certain standards. I would love to...