[NPU] Enable L1 prefix cache for Kimi-K3 W4A8 accuracy test (gpqa) (#38125)

Co-authored-by: EdwardXuy <EdwardXuy@users.noreply.github.com>
This commit is contained in:
EdwardXuy
2026-09-08 10:39:58 +08:00
committed by GitHub
co-authored by EdwardXuy
parent cf35384fe4
commit 7d2d6624b1
@@ -96,7 +96,6 @@ KIMI_K3_W4A8_32P_OTHER_ARGS = [
"triton",
"--speculative-eagle-topk",
1,
"--disable-radix-cache",
"--disable-custom-all-reduce",
"--watchdog-timeout",
9000,