uses high cpu, high memory ram, and super slowly response

[Vance-ng-vn]

Im using Mx-linux Running Rift with gpt-3.5-turbo

• Rift uses almost all of my laptop's cpu and ram Even if the rift server is over!

• /chat, with text "hello", it takes about 180 seconds to get a reply!

I tested the openAI response, and it only takes about 1.8 second to respond!

`import openai import time

openai.api_key = "sk-xxx"

start_time = time.time() response = openai.ChatCompletion.create( model="gpt-3.5-turbo", # Sử dụng engine tương ứng messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Tell me a joke."} ] ) end_time = time.time()

print("Response:", response.choices[0].message["content"]) print("Time taken:", end_time - start_time, "seconds") `

[benathi]

I'm encountering this issue as well.

[Patrick10203]

Me too. It is unusable on windows 10 VS Code. Crazy slow and uses all of my CPU. But it looks like only the client (plugin) is using so much resources for showing tokens. When i kill the server while generating it still continues to write all words in the plugin but very slow and 100% cpu usage.