@genai-fi/nanogpt 0.10.1 → 0.10.3

package/dist/ops/cpu/adamAdjust.js

@@ -1,19 +1,18 @@
-import { l as t, n as r, m as k, o as z } from "../../index-ZyQhjEPo.js";
-import { r as A } from "../../tensor_util-DV-FP5Q3.js";
-function C(o) {
-  const { moments: n, value: i } = o.inputs, { beta1: l, beta2: m, epsilon: u, learningRate: d } = o.attrs, e = n.shape.length, c = new Array(e).fill(0), s = n.shape.slice();
-  s[e - 1] = 1;
-  const a = c.slice();
-  a[e - 1] = 1;
-  const p = s.slice(), b = n.slice(c, s).squeeze([e - 1]), M = n.slice(a, p).squeeze([e - 1]), f = t(b, l), g = t(M, m);
-  return r(
-    k(t(f, r(z(g), u ?? 1e-8)), -d),
-    i
+import { p as k, w as t, x as i, m as w, y as z } from "../../index-DOvlwCh-.js";
+function A(c) {
+  const { moments: s, value: r } = c.inputs, { beta1: l, beta2: m, epsilon: u, learningRate: d } = c.attrs, e = s.shape.length, a = new Array(e).fill(0), n = s.shape.slice();
+  n[e - 1] = 1;
+  const o = a.slice();
+  o[e - 1] = 1;
+  const p = n.slice(), b = s.slice(a, n).squeeze([e - 1]), M = s.slice(o, p).squeeze([e - 1]), g = t(b, l), f = t(M, m);
+  return i(
+    w(t(g, i(z(f), u ?? 1e-8)), -d),
+    r
   );
 }
-const h = {
+const C = {
   kernelName: "AdamAdjust",
   backendName: "cpu",
-  kernelFunc: C
+  kernelFunc: A
 };
-A(h);
+k(C);

package/dist/ops/cpu/adamMoments.js

@@ -1,12 +1,11 @@
-import "../../index-ZyQhjEPo.js";
-import { r as p } from "../../tensor_util-DV-FP5Q3.js";
-import { s as b } from "../../stack-yOIAalTq.js";
+import { p } from "../../index-DOvlwCh-.js";
+import { s as b } from "../../stack-Cf4n9h0N.js";
 function f(t) {
-  const { moments: n, gradient: o } = t.inputs, { beta1: c, beta2: m } = t.attrs, e = n.shape.length, a = new Array(e).fill(0), s = n.shape.slice();
+  const { moments: n, gradient: c } = t.inputs, { beta1: o, beta2: m } = t.attrs, e = n.shape.length, a = new Array(e).fill(0), s = n.shape.slice();
   s[e - 1] = 1;
-  const r = a.slice();
-  r[e - 1] = 1;
-  const i = s.slice(), l = n.slice(a, s).squeeze([e - 1]), u = n.slice(r, i).squeeze([e - 1]), M = l.mul(c).add(o.mul(1 - c)), d = u.mul(m).add(o.square().mul(1 - m));
+  const i = a.slice();
+  i[e - 1] = 1;
+  const r = s.slice(), l = n.slice(a, s).squeeze([e - 1]), u = n.slice(i, r).squeeze([e - 1]), M = l.mul(o).add(c.mul(1 - o)), d = u.mul(m).add(c.square().mul(1 - m));
   return b([M, d], -1);
 }
 const g = {

package/dist/ops/cpu/appendCache.js

@@ -1,13 +1,12 @@
-import "../../index-ZyQhjEPo.js";
-import { r as d } from "../../tensor_util-DV-FP5Q3.js";
-import { c as h } from "../../concat-BHlIJeyT.js";
+import { p as d } from "../../index-DOvlwCh-.js";
+import { c as h } from "../../concat-BV8bt5H-.js";
 function u(p) {
-  const { cache: n, item: s } = p.inputs, { maxSize: a, pastLen: c } = p.attrs, t = n.shape[0], o = n.shape[1], r = n.shape[3], e = s.shape[2];
-  if (c + e <= a) {
-    const m = n.slice([0, 0, 0, 0], [t, o, c, r]), f = n.slice([0, 0, c + e, 0], [t, o, a - c - e, r]), i = e < e ? s.slice([0, 0, 0, 0], [t, o, e, r]) : s, k = h([m, i, f], 2);
-    return m.dispose(), f.dispose(), i !== s && i.dispose(), k;
+  const { cache: n, item: s } = p.inputs, { maxSize: i, pastLen: c } = p.attrs, t = n.shape[0], o = n.shape[1], a = n.shape[3], e = s.shape[2];
+  if (c + e <= i) {
+    const f = n.slice([0, 0, 0, 0], [t, o, c, a]), m = n.slice([0, 0, c + e, 0], [t, o, i - c - e, a]), r = e < e ? s.slice([0, 0, 0, 0], [t, o, e, a]) : s, k = h([f, r, m], 2);
+    return f.dispose(), m.dispose(), r !== s && r.dispose(), k;
   }
-  const l = n.slice([0, 0, e, 0], [t, o, a - e, r]), C = h([l, s], 2);
+  const l = n.slice([0, 0, e, 0], [t, o, i - e, a]), C = h([l, s], 2);
   return l.dispose(), C;
 }
 const w = {

package/dist/ops/cpu/attentionMask.js

@@ -1,11 +1,11 @@
-import { i as d, b as u } from "../../index-ZyQhjEPo.js";
-import { r as o } from "../../tensor_util-DV-FP5Q3.js";
-import { l as N, w as b } from "../../ops-CNI3TwqM.js";
-import { o as A } from "../../ones-CAMiP4I2.js";
-import { z as I } from "../../zeros-2gldETuK.js";
-import { m as g } from "../../mat_mul-DeAh4uTH.js";
+import { p as o, q as d, b as u } from "../../index-DOvlwCh-.js";
+import { l as N } from "../../ops-B5yanEdW.js";
+import { o as b } from "../../ones-D2rT0xk2.js";
+import { z as A } from "../../zeros-KnWaWf-X.js";
+import { w as I } from "../../resize_nearest_neighbor-B19mCEg2.js";
+import { m as g } from "../../mat_mul-SjpJRLyL.js";
 function a(n) {
-  const { q: s, k: e } = n.inputs, { divisor: r } = n.attrs, c = s.shape[2], t = e.shape[2], m = N.bandPart(A([t, t]), -1, 0).cast("bool"), i = I([t, t]), l = d([t, t], Number.NEGATIVE_INFINITY), f = b(m, i, l), k = g(s, e, !1, !0).mul(u(r)), p = f.slice([0, 0], [c, t]).expandDims(0).expandDims(0);
+  const { q: s, k: e } = n.inputs, { divisor: r } = n.attrs, c = s.shape[2], t = e.shape[2], m = N.bandPart(b([t, t]), -1, 0).cast("bool"), i = A([t, t]), l = d([t, t], Number.NEGATIVE_INFINITY), f = I(m, i, l), k = g(s, e, !1, !0).mul(u(r)), p = f.slice([0, 0], [c, t]).expandDims(0).expandDims(0);
   return k.add(p);
 }
 const w = {

package/dist/ops/cpu/fusedSoftmax.js

@@ -1,30 +1,29 @@
-import "../../index-ZyQhjEPo.js";
-import { r as e } from "../../tensor_util-DV-FP5Q3.js";
-import { s as m } from "../../softmax-ZHVebtR1.js";
-function o(t) {
-  const { inputs: s, attrs: a } = t, { logits: n } = s, { dim: i, dropoutRate: r } = a;
-  if (!n)
+import { p as e } from "../../index-DOvlwCh-.js";
+import { s as m } from "../../softmax-CA5jFsLR.js";
+function n(t) {
+  const { inputs: s, attrs: a } = t, { logits: o } = s, { dim: i, dropoutRate: r } = a;
+  if (!o)
     throw new Error("Error in softmax: input logits is null");
-  return r !== void 0 && r > 0 && console.warn("Dropout in fusedSoftmax not implemented for CPU backend, skipping dropout."), m(n, i);
+  return r !== void 0 && r > 0 && console.warn("Dropout in fusedSoftmax not implemented for CPU backend, skipping dropout."), m(o, i);
 }
 const f = {
   kernelName: "FusedSoftmax",
   backendName: "cpu",
-  kernelFunc: o
+  kernelFunc: n
 };
 e(f);
 const u = {
   kernelName: "FusedSoftmax",
   backendName: "tensorflow",
-  kernelFunc: o
+  kernelFunc: n
 };
 e(u);
 const l = {
   kernelName: "FusedSoftmax",
   backendName: "webgpu",
-  kernelFunc: o
+  kernelFunc: n
 };
 e(l);
 export {
-  o as softmaxCPU
+  n as softmaxCPU
 };

package/dist/ops/cpu/gatherSub.js

@@ -1,15 +1,14 @@
-import { A as u, B as c, E as m, c as g } from "../../index-ZyQhjEPo.js";
-import { k as p, r as h } from "../../tensor_util-DV-FP5Q3.js";
-import { r as f } from "../../range-BMS52eQi.js";
-import { s as l } from "../../stack-yOIAalTq.js";
-function N(e, t) {
-  const n = c(t, "indices", "gatherND", "int32"), r = { params: c(e, "x", "gatherND", "string_or_numeric"), indices: n };
-  return m.runKernel(p, r);
+import { A as u, B as c, E as g, aj as p, p as h, c as m } from "../../index-DOvlwCh-.js";
+import { r as l } from "../../range-BklejeeW.js";
+import { s as N } from "../../stack-Cf4n9h0N.js";
+function f(e, t) {
+  const n = c(t, "indices", "gatherND", "int32"), s = { params: c(e, "x", "gatherND", "string_or_numeric"), indices: n };
+  return g.runKernel(p, s);
 }
-const b = /* @__PURE__ */ u({ gatherND_: N });
+const b = /* @__PURE__ */ u({ gatherND_: f });
 function d(e) {
-  const { values: t, labels: n, logits: s } = e.inputs, r = n.shape[0], o = f(0, r, 1, "int32"), i = l([o, n], 1), a = b(s, i);
-  return g(t, a);
+  const { values: t, labels: n, logits: r } = e.inputs, s = n.shape[0], a = l(0, s, 1, "int32"), i = N([a, n], 1), o = b(r, i);
+  return m(t, o);
 }
 const k = {
   kernelName: "EfficientGatherSub",

package/dist/ops/cpu/gelu.js

@@ -1,8 +1,7 @@
-import { t as d } from "../../index-ZyQhjEPo.js";
-import { r } from "../../tensor_util-DV-FP5Q3.js";
+import { p as t, t as d } from "../../index-DOvlwCh-.js";
 const o = 0.7978845608028654, c = 0.044715;
-function m(t) {
-  const { inputs: u } = t, { x: n } = u, e = n;
+function m(r) {
+  const { inputs: u } = r, { x: n } = u, e = n;
   return d(() => {
     const l = e.pow(3), s = e.add(l.mul(c)).mul(o).tanh().add(1).mul(0.5);
     return e.mul(s);
@@ -13,15 +12,15 @@ const N = {
   backendName: "cpu",
   kernelFunc: m
 };
-r(N);
+t(N);
 const K = {
   kernelName: "Gelu",
   backendName: "tensorflow",
   kernelFunc: m
 };
-r(K);
-function i(t) {
-  const { dy: u, x: n } = t.inputs;
+t(K);
+function i(r) {
+  const { dy: u, x: n } = r.inputs;
   return d(() => {
     const e = n.square(), l = e.mul(n), a = n.add(l.mul(c)).mul(o).tanh(), f = a.square().neg().add(1), k = e.mul(3 * c).add(1), g = a.add(1).mul(0.5), G = n.mul(f).mul(o).mul(k).mul(0.5), p = g.add(G);
     return u.mul(p);
@@ -32,10 +31,10 @@ const x = {
   backendName: "cpu",
   kernelFunc: i
 };
-r(x);
+t(x);
 const h = {
   kernelName: "GeluGrad",
   backendName: "tensorflow",
   kernelFunc: i
 };
-r(h);
+t(h);

package/dist/ops/cpu/matMul16.js

@@ -1,16 +1,15 @@
 import { isPackedTensor as t } from "../../utilities/packed.js";
-import "../../index-ZyQhjEPo.js";
-import { r as p } from "../../tensor_util-DV-FP5Q3.js";
-import { m } from "../../mat_mul-DeAh4uTH.js";
-function l(r) {
-  const { A: e, B: n } = r.inputs, { transposeA: o, transposeB: s } = r.attrs, a = !t(e), c = !t(n);
+import { p } from "../../index-DOvlwCh-.js";
+import { m as l } from "../../mat_mul-SjpJRLyL.js";
+function m(e) {
+  const { A: n, B: r } = e.inputs, { transposeA: o, transposeB: s } = e.attrs, a = !t(n), c = !t(r);
   if (a && c)
-    return m(e, n, o, s);
+    return l(n, r, o, s);
   throw new Error("MatMul16 CPU kernel only supports packed tensors currently.");
 }
 const u = {
   kernelName: "MatMul16",
   backendName: "cpu",
-  kernelFunc: l
+  kernelFunc: m
 };
 p(u);

package/dist/ops/cpu/matMulGelu.js

@@ -1,12 +1,11 @@
-import { t as m } from "../../index-ZyQhjEPo.js";
-import { g as i, d as M } from "../../gelu-CNLFZWea.js";
-import { r as e } from "../../tensor_util-DV-FP5Q3.js";
-import { m as k } from "../../mat_mul-DeAh4uTH.js";
+import { p as e, t as m } from "../../index-DOvlwCh-.js";
+import { g as M, d as i } from "../../gelu-CjNPL4OH.js";
+import { m as k } from "../../mat_mul-SjpJRLyL.js";
 function c(t) {
   const { inputs: u } = t, { x: n, kernel: r } = u, a = n, l = r;
   return m(() => {
     const o = k(a, l);
-    return i(o);
+    return M(o);
   });
 }
 const G = {
@@ -30,7 +29,7 @@ e(p);
 function s(t) {
   const { dy: u, x: n, kernel: r } = t.inputs;
   return m(() => {
-    const a = k(n, r), l = M(u, a), o = l.matMul(r.transpose()), d = n.transpose().matMul(l);
+    const a = k(n, r), l = i(u, a), o = l.matMul(r.transpose()), d = n.transpose().matMul(l);
     return [o, d];
   });
 }

package/dist/ops/cpu/matMulMul.js

@@ -1,8 +1,7 @@
-import { t as M } from "../../index-ZyQhjEPo.js";
-import { r as e } from "../../tensor_util-DV-FP5Q3.js";
+import { p as e, t as i } from "../../index-DOvlwCh-.js";
 function n(t) {
-  const { inputs: r, attrs: l } = t, { transposeA: o, transposeB: s } = l, { x: u, kernel: a, y: c } = r, m = u, i = a, k = c;
-  return M(() => m.matMul(i, o, s).mul(k));
+  const { inputs: r, attrs: l } = t, { transposeA: o, transposeB: s } = l, { x: u, kernel: a, y: c } = r, m = u, k = a, M = c;
+  return i(() => m.matMul(k, o, s).mul(M));
 }
 const p = {
   kernelName: "MatMulMul",

package/dist/ops/cpu/mulDropout.js

@@ -1,8 +1,7 @@
-import { m as u } from "../../index-ZyQhjEPo.js";
-import { r as e } from "../../tensor_util-DV-FP5Q3.js";
+import { p as e, m as t } from "../../index-DOvlwCh-.js";
 function n(o) {
-  const { inputs: r } = o, { a: l, b: t } = r;
-  return console.warn("Using fallback mulDrop implementation without dropout."), u(l, t);
+  const { inputs: r } = o, { a: l, b: u } = r;
+  return console.warn("Using fallback mulDrop implementation without dropout."), t(l, u);
 }
 const a = {
   kernelName: "MulDropout",

package/dist/ops/cpu/normRMS.js

@@ -1,29 +1,28 @@
-import { t as d } from "../../index-ZyQhjEPo.js";
-import { r as a } from "../../tensor_util-DV-FP5Q3.js";
+import { p as o, t as d } from "../../index-DOvlwCh-.js";
 function i(t) {
-  const { inputs: e } = t, { x: n, gamma: s } = e, r = n, m = s;
+  const { inputs: e } = t, { x: n, gamma: s } = e, r = n, a = s;
   return d(() => {
     const u = r.square().mean(-1, !0).add(1e-8).rsqrt();
-    return r.mul(u).mul(m);
+    return r.mul(u).mul(a);
   });
 }
-const k = {
+const f = {
   kernelName: "RMSNorm",
   backendName: "cpu",
   kernelFunc: i
 };
-a(k);
+o(f);
 const g = {
   kernelName: "RMSNorm",
   backendName: "tensorflow",
   kernelFunc: i
 };
-a(g);
+o(g);
 function N(t) {
   const { dy: e, x: n, gamma: s } = t.inputs;
   return d(() => {
-    const r = n.shape[n.shape.length - 1], m = n.square().mean(-1, !0), o = m.add(1e-8).rsqrt(), u = n.mul(o), l = e.mul(u).sum([0, 1]), c = e.mul(s), f = c.mul(n).sum(-1, !0).div(r);
-    return [c.mul(o).sub(n.mul(f).mul(o).div(m.add(1e-8))), l];
+    const r = n.shape[n.shape.length - 1], a = n.square().mean(-1, !0), m = a.add(1e-8).rsqrt(), u = n.mul(m), l = e.mul(u).sum([0, 1]), c = e.mul(s), k = c.mul(n).sum(-1, !0).div(r);
+    return [c.mul(m).sub(n.mul(k).mul(m).div(a.add(1e-8))), l];
   });
 }
 const S = {
@@ -31,10 +30,10 @@ const S = {
   backendName: "cpu",
   kernelFunc: N
 };
-a(S);
+o(S);
 const p = {
   kernelName: "RMSNormGrad",
   backendName: "tensorflow",
   kernelFunc: N
 };
-a(p);
+o(p);

package/dist/ops/cpu/qkv.js

@@ -1,7 +1,6 @@
-import "../../index-ZyQhjEPo.js";
-import { r as q } from "../../tensor_util-DV-FP5Q3.js";
-import { r as o } from "../../reshape-DevtBWtf.js";
-import { s as x } from "../../split-DrfihRpZ.js";
+import { p as q } from "../../index-DOvlwCh-.js";
+import { r as o } from "../../reshape-ByE68wS9.js";
+import { s as x } from "../../split-CVLc0w--.js";
 function v(p) {
   const { x: c, kernel: K } = p.inputs, { heads: n, packed: C } = p.attrs;
   if (C)
@@ -10,18 +9,18 @@ function v(p) {
   a.dispose();
   const d = o(i, [s, e, 3 * t]);
   i.dispose();
-  const [k, m, l] = x(d, 3, -1);
+  const [k, l, m] = x(d, 3, -1);
   d.dispose();
   const r = t / n, f = o(k, [s, e, n, r]);
   k.dispose();
   const w = f.transpose([0, 2, 1, 3]);
   f.dispose();
-  const h = o(m, [s, e, n, r]);
-  m.dispose();
+  const h = o(l, [s, e, n, r]);
+  l.dispose();
   const N = h.transpose([0, 2, 1, 3]);
   h.dispose();
-  const u = o(l, [s, e, n, r]);
-  l.dispose();
+  const u = o(m, [s, e, n, r]);
+  m.dispose();
   const T = u.transpose([0, 2, 1, 3]);
   return u.dispose(), [w, N, T];
 }

package/dist/ops/cpu/rope.js

@@ -1,9 +1,8 @@
-import "../../index-ZyQhjEPo.js";
-import { r as I } from "../../tensor_util-DV-FP5Q3.js";
-import { r as y } from "../../range-BMS52eQi.js";
-import { g as F } from "../../gather-DykLGqmW.js";
-import { s as E } from "../../stack-yOIAalTq.js";
-import { c as T } from "../../concat-BHlIJeyT.js";
+import { p as I } from "../../index-DOvlwCh-.js";
+import { r as y } from "../../range-BklejeeW.js";
+import { g as F } from "../../gather-D3JcZUaI.js";
+import { s as E } from "../../stack-Cf4n9h0N.js";
+import { c as T } from "../../concat-BV8bt5H-.js";
 function U(c, r, p, e, n) {
   const t = e.shape[3], s = p;
   if (s > t) return e;

package/dist/ops/cpu/scatterSub.js

@@ -1,25 +1,23 @@
-import { A as f, B as c, E as g, c as l, m as N } from "../../index-ZyQhjEPo.js";
-import { j as b, r as S } from "../../tensor_util-DV-FP5Q3.js";
-import { d as h } from "../../tensor-DdQUJZlz.js";
-import { v as D } from "../../scatter_nd_util-5EL-8VAQ.js";
-import { r as k } from "../../range-BMS52eQi.js";
-import { s as v } from "../../stack-yOIAalTq.js";
-import { o as E } from "../../ones-CAMiP4I2.js";
-function I(r, e, s) {
-  h(s);
-  const n = c(r, "indices", "scatterND", "int32"), t = c(e, "updates", "scatterND");
+import { A as f, C as g, B as r, E as l, ai as N, p as b, c as S, m as h } from "../../index-DOvlwCh-.js";
+import { v as D } from "../../scatter_nd_util-lvSiX8q4.js";
+import { r as k } from "../../range-BklejeeW.js";
+import { s as v } from "../../stack-Cf4n9h0N.js";
+import { o as E } from "../../ones-D2rT0xk2.js";
+function I(a, e, s) {
+  g(s);
+  const n = r(a, "indices", "scatterND", "int32"), t = r(e, "updates", "scatterND");
   D(t, n, s);
-  const o = { indices: n, updates: t }, a = { shape: s };
-  return g.runKernel(b, o, a);
+  const c = { indices: n, updates: t }, o = { shape: s };
+  return l.runKernel(N, c, o);
 }
-const K = /* @__PURE__ */ f({ scatterND_: I });
-function L(r) {
-  const { logits: e, labels: s, dy: n } = r.inputs, t = s.shape[0], o = e.shape[1], a = k(0, t, 1, "int32"), i = v([a, s], 1), d = E([t]), p = K(i, d, [t, o]), u = l(e, p), m = n.reshape([t, 1]);
-  return N(u, m);
+const C = /* @__PURE__ */ f({ scatterND_: I });
+function K(a) {
+  const { logits: e, labels: s, dy: n } = a.inputs, t = s.shape[0], c = e.shape[1], o = k(0, t, 1, "int32"), i = v([o, s], 1), d = E([t]), u = C(i, d, [t, c]), p = S(e, u), m = n.reshape([t, 1]);
+  return h(p, m);
 }
-const T = {
+const L = {
   kernelName: "EfficientScatterSub",
   backendName: "cpu",
-  kernelFunc: L
+  kernelFunc: K
 };
-S(T);
+b(L);

package/dist/ops/dot16.js

@@ -1,8 +1,8 @@
-import { b as d } from "../matMul16--R5hOwDG.js";
+import { b as d } from "../matMul16-BWRSOCWB.js";
 import { transpose16 as w } from "./transpose16.js";
 import { reshape16 as n } from "./reshape16.js";
 import { isPackedTensor as p } from "../utilities/packed.js";
-import { d as x } from "../tfjs_backend-kNyO5L2d.js";
+import { d as x } from "../tfjs_backend-y1cvNhLA.js";
 function E(e, s, h = !1, c = !1) {
   if (!p(e) && !p(s))
     return x(e, s);

package/dist/ops/gatherSub.js

@@ -1,4 +1,4 @@
-import { e as n } from "../index-ZyQhjEPo.js";
+import { e as n } from "../index-DOvlwCh-.js";
 import "./cpu/gatherSub.js";
 import "./webgl/gatherSub.js";
 function f(r, e, t) {

package/dist/ops/gelu.js

@@ -1,7 +1,7 @@
-import "../index-ZyQhjEPo.js";
+import "../index-DOvlwCh-.js";
 import "./cpu/gelu.js";
 import "./webgl/gelu.js";
-import { d as e, g as i } from "../gelu-CNLFZWea.js";
+import { d as e, g as i } from "../gelu-CjNPL4OH.js";
 export {
   e as dGelu,
   i as gelu

package/dist/ops/grads/add16.js

@@ -1,27 +1,26 @@
-import { j as u, q as d } from "../../index-ZyQhjEPo.js";
-import { sum16 as p } from "../sum16.js";
-import { reshape16 as c } from "../reshape16.js";
-import { a as h } from "../../tensor_util-DV-FP5Q3.js";
-const m = {
+import { u as i, a3 as h, a4 as d } from "../../index-DOvlwCh-.js";
+import { sum16 as c } from "../sum16.js";
+import { reshape16 as p } from "../reshape16.js";
+const A = {
   kernelName: "Add16",
   inputsToSave: ["a", "b"],
-  gradFunc: (s, i) => {
-    const [t, a] = i, n = u(t.shape, a.shape);
+  gradFunc: (s, u) => {
+    const [t, a] = u, n = h(t.shape, a.shape);
     if (Array.isArray(s))
       throw new Error("Add16 gradFunc expected dy to be a Tensor but got an array");
     return { a: () => {
       let e = s;
       const r = d(t.shape, n);
-      r.length > 0 && (e = p(e, r));
-      const o = c(e, t.shape);
+      r.length > 0 && (e = c(e, r));
+      const o = p(e, t.shape);
       return e.dispose(), o;
     }, b: () => {
       let e = s;
       const r = d(a.shape, n);
-      r.length > 0 && (e = p(e, r));
-      const o = c(e, a.shape);
+      r.length > 0 && (e = c(e, r));
+      const o = p(e, a.shape);
       return e.dispose(), o;
     } };
   }
 };
-h(m);
+i(A);

package/dist/ops/grads/attentionMask.js

@@ -1,7 +1,6 @@
-import "../../index-ZyQhjEPo.js";
-import { m as o } from "../../matMul16--R5hOwDG.js";
-import { transpose16 as m } from "../transpose16.js";
-import { a as c } from "../../tensor_util-DV-FP5Q3.js";
+import { u as m } from "../../index-DOvlwCh-.js";
+import { m as o } from "../../matMul16-BWRSOCWB.js";
+import { transpose16 as c } from "../transpose16.js";
 const l = {
   kernelName: "AttentionMask",
   inputsToSave: ["q", "k"],
@@ -13,10 +12,10 @@ const l = {
     return {
       q: () => o(r, i, e),
       k: () => {
-        const t = o(a, r, e, !0, !1), u = m(t, [0, 1, 3, 2]);
+        const t = o(a, r, e, !0, !1), u = c(t, [0, 1, 3, 2]);
         return t.dispose(), u;
       }
     };
   }
 };
-c(l);
+m(l);

package/dist/ops/grads/gelu.js

@@ -1,6 +1,5 @@
-import "../../index-ZyQhjEPo.js";
-import { a as m } from "../../gelu-CNLFZWea.js";
-import "../../tensor_util-DV-FP5Q3.js";
+import "../../index-DOvlwCh-.js";
+import { a as e } from "../../gelu-CjNPL4OH.js";
 export {
-  m as geluGradConfig
+  e as geluGradConfig
 };

package/dist/ops/grads/matMul16.js

@@ -1,9 +1,8 @@
-import "../../index-ZyQhjEPo.js";
-import { a as f } from "../../matMul16--R5hOwDG.js";
-import "../../gelu-CNLFZWea.js";
+import "../../index-DOvlwCh-.js";
+import { a } from "../../matMul16-BWRSOCWB.js";
+import "../../gelu-CjNPL4OH.js";
 import "../transpose16.js";
 import "../reshape16.js";
-import "../../tensor_util-DV-FP5Q3.js";
 export {
-  f as matMul16GradConfig
+  a as matMul16GradConfig
 };

package/dist/ops/grads/matMulGelu.js

@@ -1,18 +1,17 @@
-import { e as l } from "../../index-ZyQhjEPo.js";
-import { a as o } from "../../tensor_util-DV-FP5Q3.js";
-function i(e, r, n) {
-  return l().runKernel("MatMulGeluGrad", { dy: e, x: r, kernel: n });
+import { u as a, e as o } from "../../index-DOvlwCh-.js";
+function s(e, n, r) {
+  return o().runKernel("MatMulGeluGrad", { dy: e, x: n, kernel: r });
 }
-const s = {
+const d = {
   kernelName: "MatMulGelu",
   inputsToSave: ["x", "kernel"],
   outputsToSave: [],
-  gradFunc: (e, r) => {
-    const [n, t] = r, [u, a] = i(e, n, t);
+  gradFunc: (e, n) => {
+    const [r, u] = n, [t, l] = s(e, r, u);
     return {
-      x: () => u,
-      kernel: () => a
+      x: () => t,
+      kernel: () => l
     };
   }
 };
-o(s);
+a(d);

package/dist/ops/grads/normRMS.js

@@ -1,21 +1,20 @@
-import { e as t } from "../../index-ZyQhjEPo.js";
-import { a as g } from "../../tensor_util-DV-FP5Q3.js";
-function i(r, a, m) {
-  return t().runKernel("RMSNormGrad", { dy: r, x: a, gamma: m });
+import { u as t, e as u } from "../../index-DOvlwCh-.js";
+function g(r, a, n) {
+  return u().runKernel("RMSNormGrad", { dy: r, x: a, gamma: n });
 }
 const s = {
   kernelName: "RMSNorm",
   inputsToSave: ["x", "gamma"],
   outputsToSave: [],
   gradFunc: (r, a) => {
-    const [m, n] = a, [o, e] = i(r, m, n);
+    const [n, e] = a, [m, o] = g(r, n, e);
     return {
-      x: () => o,
-      gamma: () => e
+      x: () => m,
+      gamma: () => o
     };
   }
 };
-g(s);
+t(s);
 export {
   s as normRMSGradConfig
 };

package/dist/ops/grads/pack16.js

@@ -1,7 +1,6 @@
-import "../../index-ZyQhjEPo.js";
-import { b as t } from "../../pack16-CFUqumar.js";
-import "../../slice-D_gkkqZK.js";
-import "../../tensor_util-DV-FP5Q3.js";
+import "../../index-DOvlwCh-.js";
+import { b as i } from "../../pack16-nQ6JaLo-.js";
+import "../../slice-BfEGSH82.js";
 export {
-  t as packGradConfig
+  i as packGradConfig
 };