Use parallel kernel

app.py

@@ -8,7 +8,7 @@ mem = psutil.virtual_memory()
 
 tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
 
-model = AutoModelForSeq2SeqLM.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True).cpu().float()
+model = AutoModelForSeq2SeqLM.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True).quantize(bits=4, compile_parallel_kernel=True, parallel_num=2).cpu().float()
 
 def chat(query, history=[]):
     _, history = model.chat(tokenizer, query, history, max_length=512)