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 16, 02:00 UTC
Fix: cases with empty sparsity config (#12057)
Signed-off-by: Rahul Tuli <rahul@neuralmagic.com>
Rahul Tuli committed
Jan 15, 2025 at 04:41 UTC
cbe94391eb04aa9ae1be15711fec4eb453c1e053
1 file changed
+1
-1
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
+1
-1
@@ -113,7 +113,7 @@ class CompressedTensorsConfig(QuantizationConfig):
113
:return: A dictionary mapping target layer names to their corresponding
114
sparsity compression configurations
115
"""
116
- if (sparsity_config := config.get(SPARSITY_CONFIG_NAME)) is None:
116
+ if not (sparsity_config := config.get(SPARSITY_CONFIG_NAME)):
117
return dict()
118
119
sparsity_config = SparsityCompressionConfig.model_validate(