diff --git a/src/transformers/generation/utils.py b/src/transformers/generation/utils.py index 8dd62ace78abb9..b3e11b4597e8f9 100644 --- a/src/transformers/generation/utils.py +++ b/src/transformers/generation/utils.py @@ -1762,8 +1762,8 @@ def generate( if cache_config.backend == "quanto" and not is_optimum_quanto_available(): raise ImportError( - "You need to install `quanto` in order to use KV cache quantization with quanto backend. " - "Please install it via with `pip install quanto`" + "You need to install `optimum-quanto` in order to use KV cache quantization with quanto backend. " + "Please install it via with `pip install optimum-quanto`" ) elif cache_config.backend == "HQQ" and not is_hqq_available(): raise ImportError(