[gpt-oss] Enable gpt-oss on ampere (#22714)

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
2025-08-12 06:21:44 -04:00
parent b8a9d0e429
commit 007dd90859
10 changed files with 26 additions and 17 deletions
--- a/vllm/model_executor/layers/quantization/mxfp4.py
+++ b/vllm/model_executor/layers/quantization/mxfp4.py
@@ -42,7 +42,7 @@ class Mxfp4Config(QuantizationConfig):

    @classmethod
    def get_min_capability(cls) -> int:
-        return 90
+        return 80

    @classmethod
    def get_name(cls) -> QuantizationMethods: