@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / be66d9b125
Fork 0

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 17, 06:45 UTC

Fix warning msg on quantization (#1715)

Woosuk Kwon committed Nov 18, 2023 at 21:49 UTC be66d9b1252bdc8aa198106a819583f104928d44
1 file changed +3 -3
vllm/config.py
+3 -3
@@ -137,9 +137,9 @@ class ModelConfig:
137 raise ValueError(
138 f"Unknown quantization method: {self.quantization}. Must "
139 f"be one of {supported_quantization}.")
140 - logger.warning(f"{self.quantization} quantization is not fully "
141 - "optimized yet. The speed can be slower than "
142 - "non-quantized models.")
140 + logger.warning(f"{self.quantization} quantization is not fully "
141 + "optimized yet. The speed can be slower than "
142 + "non-quantized models.")
143
144 def verify_with_parallel_config(
145 self,