/*
 * Copyright (c) 2025 by FlashInfer team.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *   http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
#include <flashinfer/gemm/gemm_groupwise_sm100.cuh>

using namespace flashinfer;
using namespace flashinfer::gemm;

namespace flashinfer {
namespace gemm {

{% for scale_granularity_m in [1, 128] %}
{% for scale_granularity_n in [128] %}
{% for scale_granularity_k in [128] %}
template cudaError_t
CutlassGroupwiseScaledGEMMSM100<
    {{ scale_granularity_m }},
    {{ scale_granularity_n }},
    {{ scale_granularity_k }},
    {{ scale_major_k }},
    {{ mma_sm }},
    {{ dtype_in }},
    {{ dtype_out }}>(
        void* float_buffer, size_t float_buffer_size_in_bytes,
        {{ dtype_in }}* A_ptr, {{ dtype_in }}* B_ptr, float* SFA_ptr, float* SFB_ptr,
        {{ dtype_out }}* C_ptr, int m, int n, int k, int l, cudaStream_t stream);
{% endfor %}
{% endfor %}
{% endfor %}

};  // namespace gemm
};  // namespace flashinfer