from __future__ import annotations

import torch

try:
    import triton
    import triton.language as tl
except ImportError:  # pragma: no cover - depends on local environment
    triton = None
    tl = None


TRITON_AVAILABLE = triton is not None


if TRITON_AVAILABLE:

    @triton.jit
    def vector_add_kernel(
        x_ptr,
        y_ptr,
        out_ptr,
        num_elements,
        block_size: tl.constexpr,
    ):
        pid = tl.program_id(axis=0)
        offsets = pid * block_size + tl.arange(0, block_size)
        mask = offsets < num_elements
        # TODO(student): load x and y using masked tl.load calls.
        # TODO(student): add the vectors.
        # TODO(student): write the result with tl.store.
        pass


def triton_vector_add(x: torch.Tensor, y: torch.Tensor, block_size: int = 1024) -> torch.Tensor:
    """Student entrypoint for the Triton vector add task."""
    if not TRITON_AVAILABLE:
        raise RuntimeError("Triton is not installed in this environment.")
    if x.shape != y.shape:
        raise ValueError(f"shape mismatch: {x.shape} vs {y.shape}")
    if not x.is_cuda or not y.is_cuda:
        raise ValueError("Triton kernels in this lab expect CUDA tensors.")
    raise NotImplementedError("TODO(student): launch vector_add_kernel and return the output tensor.")