# Copyright 2025 Tencent Inc. All Rights Reserved.
#
# 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.

import torch
import triton
import triton.language as tl

# modified from https://github.com/deepseek-ai/DeepSeek-V3/blob/main/inference/kernel.py
fp8_gemm_configs = [
    triton.Config(
        {"BLOCK_SIZE_M": block_m, "BLOCK_SIZE_N": block_n, "BLOCK_SIZE_K": 128},
        num_stages=num_stages,
        num_warps=8,
    )
    for block_m in [16, 32, 64]
    for block_n in [32, 64, 128]
    for num_stages in [3, 4, 5, 6]
]


@triton.autotune(configs=fp8_gemm_configs, key=["N", "K"])
@triton.jit
def _fp8_gemm_triton_block_kernel(
    a_ptr,
    b_ptr,
    c_ptr,
    a_s_ptr,
    b_s_ptr,
    M,
    N: tl.constexpr,
    K: tl.constexpr,
    BLOCK_SIZE_M: tl.constexpr,
    BLOCK_SIZE_N: tl.constexpr,
    BLOCK_SIZE_K: tl.constexpr,
):
    """
    Performs a matrix multiplication operation on FP8 matrices with scaling factors.
    """
    pid_m = tl.program_id(axis=0)
    pid_n = tl.program_id(axis=1)
    k = tl.cdiv(K, BLOCK_SIZE_K)
    offs_m = (pid_m * BLOCK_SIZE_M + tl.arange(0, BLOCK_SIZE_M)) % M
    offs_n = (pid_n * BLOCK_SIZE_N + tl.arange(0, BLOCK_SIZE_N)) % N
    offs_k = tl.arange(0, BLOCK_SIZE_K)
    a_ptrs = a_ptr + offs_m[:, None] * K + offs_k[None, :]
    b_ptrs = b_ptr + offs_n[None, :] * K + offs_k[:, None]
    a_s_ptrs = a_s_ptr + offs_m * k
    b_s_ptrs = b_s_ptr + (offs_n // BLOCK_SIZE_K) * k

    accumulator = tl.zeros((BLOCK_SIZE_M, BLOCK_SIZE_N), dtype=tl.float32)
    for i in range(k):
        a = tl.load(a_ptrs, mask=offs_k[None, :] < K - i * BLOCK_SIZE_K, other=0.0)
        b = tl.load(b_ptrs, mask=offs_k[:, None] < K - i * BLOCK_SIZE_K, other=0.0)
        a_s = tl.load(a_s_ptrs)
        b_s = tl.load(b_s_ptrs)

        accumulator += tl.dot(a, b) * a_s[:, None] * b_s[None, :]
        a_ptrs += BLOCK_SIZE_K
        b_ptrs += BLOCK_SIZE_K
        a_s_ptrs += 1
        b_s_ptrs += 1
    c = accumulator.to(c_ptr.dtype.element_ty)
    offs_m = pid_m * BLOCK_SIZE_M + tl.arange(0, BLOCK_SIZE_M)
    offs_n = pid_n * BLOCK_SIZE_N + tl.arange(0, BLOCK_SIZE_N)
    c_ptrs = c_ptr + offs_m[:, None] * N + offs_n[None, :]
    mask = (offs_m[:, None] < M) & (offs_n[None, :] < N)
    tl.store(c_ptrs, c, mask=mask)


# triton fp8 gemm for fp8 per-block weight & fp8 per-group activation
# modified from https://github.com/deepseek-ai/DeepSeek-V3/blob/main/inference/kernel.py
def fp8_gemm_triton_block(
    a: torch.Tensor,
    a_s: torch.Tensor,
    b: torch.Tensor,
    b_s: torch.Tensor,
    out_dtype=torch.bfloat16,
    bias=None,
) -> torch.Tensor:
    """
    Perform a matrix multiplication using FP8 precision.
    """
    assert a.is_contiguous() and b.is_contiguous()
    assert a_s.is_contiguous() and b_s.is_contiguous()
    K = a.size(-1)
    M = a.numel() // K
    N = b.size(0)
    c = a.new_empty(*a.size()[:-1], N, dtype=out_dtype)

    def grid(meta):
        return (
            triton.cdiv(M, meta["BLOCK_SIZE_M"]),
            triton.cdiv(N, meta["BLOCK_SIZE_N"]),
        )

    _fp8_gemm_triton_block_kernel[grid](a, b, c, a_s, b_s, M, N, K)

    if bias is not None:
        c += bias

    return c