llmengine/base_chat_llm.py

@@ -150,14 +150,14 @@ class BaseChatLLM:
 		for d in self.output_generator(streamer):
 			if i == 0:
 				i = 1
-				t2 = time()
+				t1 = time()
 			if d['choices'][0]['finish_reason'] != 'stop':
 				txt += d['choices'][0]['delta']['content']
 			else:
 				o_tokens = d.get('output_tokens', 0)
 		i_tokens  = input_len
 
-		t3 = time()
+		t2 = time()
 		return {
 			'id': f'chatcmpl-{getID()}',
 			"object":"chat.completion",

llmengine/server.py

@@ -8,7 +8,7 @@ from llmengine.gemma3_it import Gemma3LLM
 from llmengine.medgemma3_it import MedgemmaLLM
 from llmengine.qwen3 import Qwen3LLM
 from llmengine.qwen3coder import Qwen3CoderLLM
-from llmengine.baichuanm2 import BaichuanM2LLM
+from llmengine.baiduanm2 import BaichuanM2LLM
 
 from appPublic.registerfunction import RegisterFunction
 from appPublic.log import debug, exception