From 0ed27ef66ca7d7fec3c9bb8e33709ade1c73b4ad Mon Sep 17 00:00:00 2001 From: a2q1p Date: Wed, 30 Apr 2025 00:23:39 +0800 Subject: [PATCH] Fix: Spelling of inference (#17387) --- .../quantization/compressed_tensors/compressed_tensors.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py index 7b0032572ecf3..5be6b22c7b234 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py @@ -384,7 +384,7 @@ class CompressedTensorsConfig(QuantizationConfig): Detect whether a layer_name is found in any target and use the quantization scheme corresponding to the matched target - to select the CompressedTensorsScheme used for infernece. + to select the CompressedTensorsScheme used for inference. """ # Find the "target" in the compressed-tensors config