Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion vllm/config.py
Original file line number Diff line number Diff line change
Expand Up @@ -212,7 +212,7 @@ def _verify_quantization(self) -> None:
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 "
Expand Down