[MISC] Remove FP8 warning (#5472)

Co-authored-by: Philipp Moritz <pcmoritz@gmail.com>
2024-06-13 11:22:30 -07:00 · 2024-06-13 11:22:30 -07:00 · 30299a41fa
commit 30299a41fa
parent 85657b5607
1 changed files with 1 additions and 1 deletions
--- a/vllm/config.py
+++ b/vllm/config.py
@ -212,7 +212,7 @@ class ModelConfig:
                    f"{self.quantization} quantization is currently not "
                    f"supported in ROCm.")
            if (self.quantization
-                    not in ["marlin", "gptq_marlin_24", "gptq_marlin"]):
+                    not in ("fp8", "marlin", "gptq_marlin_24", "gptq_marlin")):
                logger.warning(
                    "%s quantization is not fully "
                    "optimized yet. The speed can be slower than "