Add Llama4 support (#5092)

Co-authored-by: Cheng Wan <cwan39@gatech.edu> Co-authored-by: fzyzcjy <ch271828n@outlook.com> Co-authored-by: ispobock <ispobaoke@163.com>
2025-04-07 00:29:36 -07:00
parent d1bb171180
commit f04c80dc42
27 changed files with 2214 additions and 22 deletions
--- a/python/sglang/srt/layers/quantization/init.py
+++ b/python/sglang/srt/layers/quantization/init.py
@@ -280,6 +280,7 @@ def monkey_patch_moe_apply(class_obj: "FusedMoEMethodBase"):
        custom_routing_function: Optional[Callable] = None,
        correction_bias: Optional[torch.Tensor] = None,
        activation: str = "silu",
+        apply_router_weight_on_input: bool = False,
        inplace: bool = True,
        no_combine: bool = False,
    ):