update usage of trtllm_fp8_per_tensor_scale_moe (#12569)

2025-11-03 14:25:32 -08:00
parent 8834260739
commit d31d48b341
2 changed files with 2 additions and 2 deletions
--- a/python/sglang/srt/layers/quantization/modelopt_quant.py
+++ b/python/sglang/srt/layers/quantization/modelopt_quant.py
@@ -689,7 +689,7 @@ class ModelOptFp8MoEMethod(FusedMoEMethodBase):
                        else 1.0
                    ),
                    use_routing_scales_on_input=use_routing_scales_on_input,
-                    tile_tokens_dim=8,  # TODO(brayden): use the FI tile calculation
+                    tile_tokens_dim=None,
                    routing_method_type=routing_method_type,
                )
                sm.tag(output)