[MoE] Retire the AOT moe_fused_gate / kimi_k2_moe_fused_gate gate kernels (#26771) (#29997)

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Xiaoyu Zhang
2026-07-07 13:53:17 +08:00
committed by GitHub
co-authored by Claude Opus 4.8
parent 9bd02dc5b9
commit 1da7d3a50b
19 changed files with 45 additions and 2499 deletions
-4
View File
@@ -93,9 +93,7 @@ else:
apply_shuffle_mul_sum,
fp8_blockwise_scaled_grouped_mm,
fused_qk_norm_rope,
kimi_k2_moe_fused_gate,
moe_align_block_size,
moe_fused_gate,
moe_sum,
moe_sum_reduce,
prepare_moe_input,
@@ -181,10 +179,8 @@ else:
"gptq_gemm",
"gptq_shuffle",
"int8_scaled_mm",
"kimi_k2_moe_fused_gate",
"merge_state_v2",
"moe_align_block_size",
"moe_fused_gate",
"moe_sum",
"moe_sum_reduce",
"prepare_moe_input",