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 14, 05:30 UTC
typo: remove duplicate `is` (#25641)
Signed-off-by: nicole-lihui <nicole.li@daocloud.io>
Nicole LiHui 🥜 committed
Sep 25, 2025 at 15:46 UTC
af4ee63e0e9d051e3f3756a2d33686e774503f4a
1 file changed
+2
-2
vllm/v1/engine/processor.py
+2
-2
@@ -79,7 +79,7 @@ class Processor:
79
if num_logprobs > max_logprobs:
80
raise ValueError(
81
f"Requested sample logprobs of {num_logprobs}, "
82
- f"which is is greater than max allowed: {max_logprobs}")
82
+ f"which is greater than max allowed: {max_logprobs}")
83
84
# Validate prompt logprobs.
85
if params.prompt_logprobs:
@@ -89,7 +89,7 @@ class Processor:
89
if num_prompt_logprobs > max_logprobs:
90
raise ValueError(
91
f"Requested prompt logprobs of {num_prompt_logprobs}, "
92
- f"which is is greater than max allowed: {max_logprobs}")
92
+ f"which is greater than max allowed: {max_logprobs}")
93
94
def _validate_sampling_params(
95
self,