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, 23:15 UTC
[MISC] Remove FP8 warning (#5472)
Co-authored-by: Philipp Moritz <pcmoritz@gmail.com>
Cody Yu committed
Jun 13, 2024 at 11:22 UTC
30299a41fa78c7bf485aca7ef8ad584ca340a64d
1 file changed
+1
-1
vllm/config.py
+1
-1
@@ -212,7 +212,7 @@ class ModelConfig:
212
f"{self.quantization} quantization is currently not "
213
f"supported in ROCm.")
214
if (self.quantization
215
- not in ["marlin", "gptq_marlin_24", "gptq_marlin"]):
215
+ not in ("fp8", "marlin", "gptq_marlin_24", "gptq_marlin")):
216
logger.warning(
217
"%s quantization is not fully "
218
"optimized yet. The speed can be slower than "