A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 4, 22:30 UTC
[Fix] Add Spacing when Requesting Output Token > max_model_len (#40324)
Signed-off-by: San-Nguyen <san.nguyen@ibm.com>
San-Nguyen committed
Apr 20, 2026 at 02:25 UTC
e729cc823d313aa7623ecadefe4305ea241c3dce
1 file changed
+1
-1
vllm/renderers/params.py
+1
-1
@@ -204,7 +204,7 @@ class TokenizeParams:
204
and max_output_tokens > max_total_tokens
205
):
206
raise VLLMValidationError(
207
- f"{self.max_output_tokens_param}={max_output_tokens}"
207
+ f"{self.max_output_tokens_param}={max_output_tokens} "
208
f"cannot be greater than "
209
f"{self.max_total_tokens_param}={max_total_tokens=}. "
210
f"Please request fewer output tokens.",