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, 23:45 UTC
Fixed typo in profiling logs (#21441)
Sergio Paniego Blanco committed
Jul 23, 2025 at 10:18 UTC
6364af92f8e450f8ccdeb30cc6cc57e26cd247e1
1 file changed
+1
-1
vllm/multimodal/profiling.py
+1
-1
@@ -275,7 +275,7 @@ class MultiModalProfiler(Generic[_I]):
275
if total_mm_tokens > seq_len:
276
logger.warning_once(
277
"The sequence length (%d) is smaller than the pre-defined"
278
- " wosrt-case total number of multimodal tokens (%d). "
278
+ " worst-case total number of multimodal tokens (%d). "
279
"This may cause certain multi-modal inputs to fail during "
280
"inference. To avoid this, you should increase "
281
"`max_model_len` or reduce `mm_counts`.",