xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-20 14:37:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: Lifan Shen <lifans@meta.com>
This commit is contained in:
Lifans 2025-09-10 06:16:21 -07:00 committed by GitHub
parent 492196ed0e
commit d6069887c6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/platforms/rocm.py
View File

@ -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