xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-01 17:07:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge b6520e5ec6e0aad1bec5b7d142f1e05d26c7849c into 254f6b986720c92ddf97fbb1a6a6465da8e87e29

Browse Source
This commit is contained in:
Steve Westerhouse 2025-12-25 08:06:50 +08:00 committed by GitHub
commit 1ab2ef6ebc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tests/quantization/utils.py
View File

@ -10,6 +10,10 @@ def is_quant_method_supported(quant_method: str) -> bool:
if not (current_platform.is_cuda() or current_platform.is_rocm()): if not (current_platform.is_cuda() or current_platform.is_rocm()):
return False return False
# RTN quantization is currently not supported on ROCm
if current_platform.is_rocm() and quant_method == "rtn":
return False
capability = current_platform.get_device_capability() capability = current_platform.get_device_capability()
assert capability is not None assert capability is not None