#pragma once

#include <torch/torch.h>

bool cutlass_scaled_mm_supports_fp8(int64_t cuda_device_capability);

void cutlass_scaled_mm(torch::Tensor& out, torch::Tensor const& a,
                       torch::Tensor const& b, torch::Tensor const& a_scales,
                       torch::Tensor const& b_scales,
                       c10::optional<torch::Tensor> const& bias);

void cutlass_scaled_mm_azp(torch::Tensor& out, torch::Tensor const& a,
                           torch::Tensor const& b,
                           torch::Tensor const& a_scales,
                           torch::Tensor const& b_scales,
                           torch::Tensor const& azp_adj,
                           c10::optional<torch::Tensor> const& azp,
                           c10::optional<torch::Tensor> const& bias);

void static_scaled_int8_quant(torch::Tensor& out, torch::Tensor const& input,
                              torch::Tensor const& scale,
                              c10::optional<torch::Tensor> const& azp);

void dynamic_scaled_int8_quant(torch::Tensor& out, torch::Tensor const& input,
                               torch::Tensor& scales,
                               c10::optional<torch::Tensor> const& azp);

torch::Tensor gptq_gemm(torch::Tensor a, torch::Tensor b_q_weight,
                        torch::Tensor b_gptq_qzeros,
                        torch::Tensor b_gptq_scales, torch::Tensor b_g_idx,
                        bool use_exllama, int64_t bit);

void gptq_shuffle(torch::Tensor q_weight, torch::Tensor q_perm, int64_t bit);

void static_scaled_fp8_quant(torch::Tensor& out, torch::Tensor const& input,
                             torch::Tensor const& scale);

void dynamic_scaled_fp8_quant(torch::Tensor& out, torch::Tensor const& input,
                              torch::Tensor& scale);

void dynamic_per_token_scaled_fp8_quant(
    torch::Tensor& out, torch::Tensor const& input, torch::Tensor& scale,
    c10::optional<torch::Tensor> const& scale_ub);

torch::Tensor fp8_marlin_gemm(torch::Tensor& a, torch::Tensor& b_q_weight,
                              torch::Tensor& b_scales, torch::Tensor& workspace,
                              int64_t num_bits, int64_t size_m, int64_t size_n,
                              int64_t size_k);