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 15, 12:15 UTC
Fix: Spelling of inference (#17387)
a2q1p committed
Apr 30, 2025 at 00:23 UTC
0ed27ef66ca7d7fec3c9bb8e33709ade1c73b4ad
1 file changed
+1
-1
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
+1
-1
@@ -384,7 +384,7 @@ class CompressedTensorsConfig(QuantizationConfig):
384
385
Detect whether a layer_name is found in any target and
386
use the quantization scheme corresponding to the matched target
387
- to select the CompressedTensorsScheme used for infernece.
387
+ to select the CompressedTensorsScheme used for inference.
388
"""
389
390
# Find the "target" in the compressed-tensors config