Rename triton_fused_moe -> fused_moe_triton (#2163)

2024-11-24 08:12:35 -08:00
parent fe5d3e818f
commit be0124bda0
76 changed files with 19 additions and 19 deletions
--- a/python/sglang/srt/layers/quantization/init.py
+++ b/python/sglang/srt/layers/quantization/init.py
@@ -68,7 +68,7 @@ def fp8_get_quant_method(self, layer, prefix):
        is_layer_skipped,
    )

-    from sglang.srt.layers.triton_fused_moe.layer import FusedMoE
+    from sglang.srt.layers.fused_moe_triton.layer import FusedMoE

    if isinstance(layer, LinearBase):
        if is_layer_skipped(prefix, self.ignored_layers):