[Misc] Improve the readability of BNB error messages (vllm-project#12320

) Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
EmbeddedLLM · Jan 22, 2025 · b3e2ae9 · b3e2ae9
1 parent 2e791d9
commit b3e2ae9
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/vllm/model_executor/model_loader/loader.py b/vllm/model_executor/model_loader/loader.py
@@ -1076,8 +1076,8 @@ def _load_weights(self, model_config: ModelConfig,
         # weight tensor. So TP does not work with pre_quantized bnb models.
         if pre_quant and get_tensor_model_parallel_world_size() > 1:
             raise ValueError(
-                "Prequant BitsAndBytes models with TP is not supported."
-                "Please try with PP.")
+                "Prequant BitsAndBytes models with tensor parallelism is not "
+                "supported. Please try with pipeline parallelism.")
 
         load_8bit = False
         if pre_quant: