[Kimi-K3][Bugfix] Fix low-latency GEMM fallback initialization (#54167)

Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
This commit is contained in:
Thien Tran
2026-08-28 08:32:20 +00:00
committed by GitHub
parent 9236159bb6
commit f956e1c343
2 changed files with 7 additions and 13 deletions
@@ -725,6 +725,7 @@ class _KimiK3LowLatencyApply:
"""Mixin: try the precomputed plan, else defer to the base method."""
def __init__(self, plan: dict[int, ResolvedCall]) -> None:
super().__init__()
self._plan = plan
def apply(