[Feature]: Remove Chunking From FusedMoE (#34086)

Signed-off-by: SouthWest7 <am1ao@qq.com>
Signed-off-by: Southwest <1403572259@qq.com>
Signed-off-by: southwest <am1ao@qq.com>
Signed-off-by: Xinan Miao <1403572259@qq.com>
Co-authored-by: SouthWest7 <am1ao@qq.com>
This commit is contained in:
Xinan Miao
2026-03-12 14:24:38 -04:00
committed by GitHub
co-authored by SouthWest7
parent c973ecdead
commit 2cdf92228c
28 changed files with 152 additions and 523 deletions
@@ -92,16 +92,6 @@ class FallbackExperts(mk.FusedMoEExpertsModular, ABC):
moe_parallel_config
) and fallback_cls._supports_parallel_config(moe_parallel_config)
def supports_chunking(self) -> bool:
assert (
self.experts.supports_chunking()
== self.fallback_experts.supports_chunking()
)
return (
self.experts.supports_chunking()
and self.fallback_experts.supports_chunking()
)
def supports_expert_map(self) -> bool:
assert (
self.experts.supports_expert_map()