sunxin 0dc7034ce0 [Model Runner] Deprecate not_need_stop (#6356) ...

* Deprecate not_need_stop

2026-03-05 10:55:42 +08:00

..

apply_rope_qkv.cu

[Metax] refactor cutlass moe and optimize flash attention (#5361)

2025-12-10 17:15:17 +08:00

cache_kv_with_rope.cu

[Metax] optimize flash attention backend (#5876)

2026-01-06 09:52:09 +08:00

cpp_extensions.cc

[Model Runner] Deprecate not_need_stop (#6356)

2026-03-05 10:55:42 +08:00

fused_moe_gemm_kernels.h

[Metax] adapt to gemm interface on different versions of maca (#5905)

2026-01-07 10:02:24 +08:00

fused_moe_helper.h

[Metax] refactor cutlass moe and optimize flash attention (#5361)

2025-12-10 17:15:17 +08:00

fused_moe_imp_op.h

[Metax] refactor cutlass moe and optimize flash attention (#5361)

2025-12-10 17:15:17 +08:00

fused_moe_op.h

[Metax] refactor cutlass moe and optimize flash attention (#5361)

2025-12-10 17:15:17 +08:00

fused_moe.cu

[Metax] refactor cutlass moe and optimize flash attention (#5361)

2025-12-10 17:15:17 +08:00

maca_version.h

[Metax] adapt to the latest develop (#6282)

2026-01-29 23:21:20 -08:00

moe_dispatch.cu

[Metax] refactor cutlass moe and optimize flash attention (#5361)

2025-12-10 17:15:17 +08:00

moe_ffn.cu

[Metax] refactor cutlass moe and optimize flash attention (#5361)

2025-12-10 17:15:17 +08:00

moe_reduce.cu

[Metax] refactor cutlass moe and optimize flash attention (#5361)

2025-12-10 17:15:17 +08:00

split_merge_qkv.cu

[Metax] optimize flash attention backend (#5876)

2026-01-06 09:52:09 +08:00