export declare const CONV1D_FORWARD_WGSL = "\n\nstruct ConvParams {\n    seq_len     : u32,   // L\n    d_channels  : u32,   // D (number of depthwise channels in this call)\n    kernel_size : u32,   // K (typically 4)\n    batch       : u32,   // B\n    groups      : u32,   // number of channel groups (1 = standard depthwise)\n};\n\n@group(0) @binding(0) var<uniform>             params   : ConvParams;\n// x      (B, L, D) \u2013 input\n@group(0) @binding(1) var<storage, read>       x        : array<f32>;\n// weight (D, K)    \u2013 depthwise conv weights\n@group(0) @binding(2) var<storage, read>       weight   : array<f32>;\n// bias   (D,)      \u2013 optional bias (zeros if unused)\n@group(0) @binding(3) var<storage, read>       bias     : array<f32>;\n// y      (B, L, D) \u2013 output\n@group(0) @binding(4) var<storage, read_write> y        : array<f32>;\n\n// Dispatch: (ceil(L/16), ceil(D/16), B)\n@compute @workgroup_size(16, 16, 1)\nfn conv1d_forward(\n    @builtin(global_invocation_id) gid : vec3<u32>,\n) {\n    let L  = params.seq_len;\n    let D  = params.d_channels;\n    let K  = params.kernel_size;\n    let B  = params.batch;\n\n    let t  = gid.x;   // time position\n    let d  = gid.y;   // channel\n    let b  = gid.z;   // batch\n\n    if (t >= L || d >= D || b >= B) { return; }\n\n    var acc: f32 = 0.0;\n\n    // Causal: convolve over k = 0..K-1, reading position (t - k)\n    for (var k: u32 = 0u; k < K; k = k + 1u) {\n        let w_idx = d * K + k;\n        let w_val = weight[w_idx];\n\n        // t - k: use causal zero-padding for t < k\n        if (t >= k) {\n            let src = b * L * D + (t - k) * D + d;\n            acc = acc + w_val * x[src];\n        }\n        // else: zero-padding contributes 0\n    }\n\n    acc = acc + bias[d];\n\n    let out = b * L * D + t * D + d;\n    y[out] = acc;\n}\n";
export declare const CONV1D_BACKWARD_WGSL = "\n\nstruct ConvParams {\n    seq_len     : u32,\n    d_channels  : u32,\n    kernel_size : u32,\n    batch       : u32,\n};\n\n@group(0) @binding(0) var<uniform>              params   : ConvParams;\n@group(0) @binding(1) var<storage, read>        x        : array<f32>;\n@group(0) @binding(2) var<storage, read>        weight   : array<f32>;\n@group(0) @binding(3) var<storage, read>        dy       : array<f32>;\n@group(0) @binding(4) var<storage, read_write>  dx       : array<f32>;\n@group(0) @binding(5) var<storage, read_write>  dweight  : array<f32>;\n@group(0) @binding(6) var<storage, read_write>  dbias    : array<f32>;\n\n// Dispatch: (ceil(L/16), ceil(D/16), B) \u2013 computes dx\n@compute @workgroup_size(16, 16, 1)\nfn conv1d_backward_dx(\n    @builtin(global_invocation_id) gid : vec3<u32>,\n) {\n    let L  = params.seq_len;\n    let D  = params.d_channels;\n    let K  = params.kernel_size;\n    let B  = params.batch;\n\n    let t  = gid.x;\n    let d  = gid.y;\n    let b  = gid.z;\n\n    if (t >= L || d >= D || b >= B) { return; }\n\n    var grad: f32 = 0.0;\n\n    // dx[b, t, d] = sum_{k=0}^{K-1} dy[b, t+k, d] * weight[d, k]\n    for (var k: u32 = 0u; k < K; k = k + 1u) {\n        let tp = t + k;\n        if (tp < L) {\n            let dy_idx = b * L * D + tp * D + d;\n            let w_idx  = d * K + k;\n            grad = grad + dy[dy_idx] * weight[w_idx];\n        }\n    }\n\n    let dx_idx = b * L * D + t * D + d;\n    dx[dx_idx] = grad;\n}\n\n// Dispatch: (K, D, 1) \u2013 accumulates dweight over (B, L)\n@compute @workgroup_size(1, 1, 1)\nfn conv1d_backward_dw(\n    @builtin(global_invocation_id) gid : vec3<u32>,\n) {\n    let L  = params.seq_len;\n    let D  = params.d_channels;\n    let K  = params.kernel_size;\n    let B  = params.batch;\n\n    let k  = gid.x;\n    let d  = gid.y;\n\n    if (k >= K || d >= D) { return; }\n\n    var grad_w: f32 = 0.0;\n    var grad_b: f32 = 0.0;\n\n    for (var b: u32 = 0u; b < B; b = b + 1u) {\n        for (var t: u32 = 0u; t < L; t = t + 1u) {\n            let dy_idx = b * L * D + t * D + d;\n            let dy_val = dy[dy_idx];\n            if (t >= k) {\n                let x_idx = b * L * D + (t - k) * D + d;\n                grad_w = grad_w + dy_val * x[x_idx];\n            }\n            if (k == 0u) {\n                grad_b = grad_b + dy_val;\n            }\n        }\n    }\n\n    dweight[d * K + k] = grad_w;\n    if (k == 0u) {\n        dbias[d] = grad_b;\n    }\n}\n";
//# sourceMappingURL=conv1d.d.ts.map