Skip to content

GitLab

Unverified Commit d6069887 authored by Lifans's avatar Lifans Committed by GitHub
Browse files

[rocm] enable torchao quantization for rocm (#24400) 


Signed-off-by: default avatarLifan Shen <lifans@meta.com>
parent 492196ed
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/platforms/rocm.py
View file @ d6069887
...@@ -171,7 +171,7 @@ class RocmPlatform(Platform): ...@@ -171,7 +171,7 @@ class RocmPlatform(Platform):
supported_quantization: list[str] = [ supported_quantization: list[str] = [
"awq", "gptq", "fp8", "compressed-tensors", "fbgemm_fp8", "gguf", "awq", "gptq", "fp8", "compressed-tensors", "fbgemm_fp8", "gguf",
"quark", "ptpc_fp8", "mxfp4", "petit_nvfp4" "quark", "ptpc_fp8", "mxfp4", "petit_nvfp4", "torchao"
] ]
@classmethod @classmethod
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment