foxhunt/crates/ml/examples/cuda_test.rs

#![allow(
    clippy::assertions_on_constants,
    clippy::assertions_on_result_states,
    clippy::clone_on_copy,
    clippy::decimal_literal_representation,
    clippy::doc_markdown,
    clippy::empty_line_after_doc_comments,
    clippy::field_reassign_with_default,
    clippy::get_unwrap,
    clippy::identity_op,
    clippy::inconsistent_digit_grouping,
    clippy::indexing_slicing,
    clippy::integer_division,
    clippy::len_zero,
    clippy::let_underscore_must_use,
    clippy::manual_div_ceil,
    clippy::manual_let_else,
    clippy::manual_range_contains,
    clippy::modulo_arithmetic,
    clippy::needless_range_loop,
    clippy::non_ascii_literal,
    clippy::redundant_clone,
    clippy::shadow_reuse,
    clippy::shadow_same,
    clippy::shadow_unrelated,
    clippy::single_match_else,
    clippy::str_to_string,
    clippy::string_slice,
    clippy::tests_outside_test_module,
    clippy::too_many_lines,
    clippy::unnecessary_wraps,
    clippy::unseparated_literal_suffix,
    clippy::use_debug,
    clippy::useless_vec,
    clippy::wildcard_enum_match_arm,
    clippy::else_if_without_else,
    clippy::expect_used,
    clippy::missing_const_for_fn,
    clippy::similar_names,
    clippy::type_complexity,
    clippy::collapsible_else_if,
    clippy::doc_lazy_continuation,
    clippy::items_after_test_module,
    clippy::map_clone,
    clippy::multiple_unsafe_ops_per_block,
    clippy::unwrap_or_default,
    clippy::assign_op_pattern,
    clippy::needless_borrow,
    clippy::println_empty_string,
    clippy::unnecessary_cast,
    clippy::used_underscore_binding,
    clippy::create_dir,
    clippy::implicit_saturating_sub,
    clippy::exit,
    clippy::expect_fun_call,
    clippy::too_many_arguments,
    clippy::unnecessary_map_or,
    clippy::unwrap_used,
    dead_code,
    unused_imports,
    unused_variables,
    clippy::cloned_ref_to_slice_refs,
    clippy::neg_multiply,
    clippy::while_let_loop,
    clippy::bool_assert_comparison,
    clippy::excessive_precision,
    clippy::trivially_copy_pass_by_ref,
    clippy::op_ref,
    clippy::redundant_closure,
    clippy::unnecessary_lazy_evaluations,
    clippy::if_then_some_else_none,
    clippy::unnecessary_to_owned,
    clippy::single_component_path_imports,
)]
//! Simple CUDA functionality test to verify compatibility
//!
//! This test verifies that the updated candle-core with CUDA support
//! can successfully create tensors and perform basic operations.
#![allow(unused_crate_dependencies)]

// candle eliminated — test uses native APIs
// candle eliminated — nn types replaced with CUDA autograd

/// Format a tensor's dimensions as a display string without using Debug formatting.
fn fmt_dims(dims: &[usize]) -> String {
    let parts: Vec<String> = dims.iter().map(|d| d.to_string()).collect();
    format!("[{}]", parts.join(", "))
}

/// Test basic CUDA tensor operations
pub fn test_cuda_basic() -> Result<(), Box<dyn std::error::Error>> {
    println!("Testing CUDA compatibility...");

    // Try to get CUDA device
    match Device::new_cuda(0) {
        Ok(device) => {
            println!("[OK] CUDA device 0 available");

            // Create a simple tensor
            let tensor = Tensor::randn(0_f32, 1.0, (4, 4), &device)?;
            println!("[OK] Created CUDA tensor: {}", fmt_dims(tensor.dims()));

            // Perform basic operations
            let result = tensor.matmul(&tensor.t()?)?;
            println!(
                "[OK] Matrix multiplication successful: {}",
                fmt_dims(result.dims())
            );

            Ok(())
        },
        Err(e) => {
            println!("[WARN] CUDA device not available: {}", e);
            println!("This is expected if no GPU is present, but CUDA compilation succeeded");
            Ok(())
        },
    }
}

/// Test candle-nn components with CUDA
pub fn test_cuda_neural_network() -> Result<(), Box<dyn std::error::Error>> {
    println!("Testing CUDA neural network components...");

    if let Ok(device) = Device::new_cuda(0) {
        let varmap = VarMap::new();
        let vs = VarBuilder::from_varmap(&varmap, ml_core::native_types::NativeDType::F32, &device);

        // Create a simple linear layer
        let linear_layer = linear(10, 5, vs.pp("linear"))?;
        let input = Tensor::randn(0_f32, 1.0, (1, 10), &device)?;

        let output = linear_layer.forward(&input)?;
        println!(
            "[OK] Neural network forward pass successful: {}",
            fmt_dims(output.dims())
        );
    } else {
        println!("[WARN] CUDA neural network test skipped (no GPU)");
    }

    Ok(())
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn verify_cuda_compilation() {
        // This test just verifies that CUDA code compiles
        // The actual runtime test is optional since CI may not have GPU
        println!("CUDA compilation test passed!");

        // Try to run basic test but don't fail if no GPU
        let _ = test_cuda_basic();
        let _ = test_cuda_neural_network();
    }
}

fn main() -> Result<(), Box<dyn std::error::Error>> {
    test_cuda_basic()?;
    test_cuda_neural_network()?;
    println!("[DONE] CUDA compatibility verification complete!");
    Ok(())
}