ipex-llm/python
binbin Deng e5ae6f2c13 LLM: fix truncation logic of past_key_values in chatglm multi turn chat (#10007)
* Avoid frequently truncating past_key_values  when its length is larger than required.
2024-01-26 16:56:02 +08:00
..
llm LLM: fix truncation logic of past_key_values in chatglm multi turn chat (#10007) 2024-01-26 16:56:02 +08:00