[Refactor] refactor humming linear and moe backends to use explicit layer configs (#49610)

Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
Jinzhen Lin
2026-08-07 10:03:19 -07:00
committed by GitHub
co-authored by OpenAI Codex
parent e229fdbc87
commit fcde8e1460
37 changed files with 448 additions and 341 deletions
@@ -804,7 +804,6 @@ class QuarkW8A8Int8MoEMethod(QuarkMoEMethod):
moe_config=self.moe,
experts_cls=self.experts_cls,
routing_tables=layer._expert_routing_tables(),
layer=layer,
)
def get_fused_moe_quant_config(
@@ -1646,7 +1645,6 @@ class QuarkNvfp4MoEMethod(QuarkMoEMethod):
experts_cls=self.experts_cls,
backend=self.nvfp4_backend,
routing_tables=layer._expert_routing_tables(),
layer=layer,
)
def get_fused_moe_quant_config(