[CI/Build][Bugfix]Fix Quantized Models Test on AMD (#27712)

Signed-off-by: zhewenli <zhewenli@meta.com>
This commit is contained in:
Zhewen Li
2025-10-28 23:27:30 -07:00
committed by GitHub
parent a4a4f0f617
commit 83fd49b1fc
3 changed files with 8 additions and 2 deletions

View File

@@ -413,7 +413,7 @@ class RocmPlatform(Platform):
"Using AWQ quantization with ROCm, but VLLM_USE_TRITON_AWQ"
" is not set, enabling VLLM_USE_TRITON_AWQ."
)
envs.VLLM_USE_TRITON_AWQ = True
os.environ["VLLM_USE_TRITON_AWQ"] = "1"
@classmethod
def get_punica_wrapper(cls) -> str: