@genai-fi/nanogpt 0.11.0 → 0.12.1

package/dist/ops/appendCache.js

@@ -1,9 +1,9 @@
-import { e as a } from "../index-D0RBWjq8.js";
+import { e as a } from "../index-Duu1Lvvv.js";
 import "./cpu/appendCache.js";
 import "./webgl/appendCache.js";
 import { isPackedTensor as c } from "../utilities/packed.js";
-import { c as t } from "../concat-C6X3AAlQ.js";
-import { z as f } from "../zeros-DeiE2zTa.js";
+import { c as t } from "../concat-CSm2rMwe.js";
+import { z as f } from "../zeros-5YROwwUH.js";
 function C(r, o, n, p) {
   if (!p) {
     const e = r.shape[2], s = c(r);

package/dist/ops/attentionMask.js

@@ -1,4 +1,4 @@
-import { e as r } from "../index-D0RBWjq8.js";
+import { e as r } from "../index-Duu1Lvvv.js";
 import "./cpu/attentionMask.js";
 import "./webgl/attentionMask.js";
 import "./grads/attentionMask.js";

package/dist/ops/concat16.js

@@ -1,6 +1,6 @@
 import { isPackedTensor as o } from "../utilities/packed.js";
-import { e } from "../index-D0RBWjq8.js";
-import { c } from "../concat-C6X3AAlQ.js";
+import { e } from "../index-Duu1Lvvv.js";
+import { c } from "../concat-CSm2rMwe.js";
 function p(r, n) {
   return o(r[0]) ? e().runKernel("Concat16", r, { axis: n ?? -1 }) : c(r, n);
 }

package/dist/ops/cpu/adamAdjust.js

@@ -1,18 +1,18 @@
-import { h, l as t, n as i, m as k, o as z } from "../../index-D0RBWjq8.js";
-function A(c) {
+import { f as k, j as t, l as i, m as z, n as A } from "../../index-Duu1Lvvv.js";
+function C(c) {
   const { moments: n, value: r } = c.inputs, { beta1: l, beta2: m, epsilon: u, learningRate: d } = c.attrs, e = n.shape.length, a = new Array(e).fill(0), s = n.shape.slice();
   s[e - 1] = 1;
   const o = a.slice();
   o[e - 1] = 1;
-  const b = s.slice(), p = n.slice(a, s).squeeze([e - 1]), M = n.slice(o, b).squeeze([e - 1]), g = t(p, l), f = t(M, m);
+  const b = s.slice(), p = n.slice(a, s).squeeze([e - 1]), M = n.slice(o, b).squeeze([e - 1]), f = t(p, l), g = t(M, m);
   return i(
-    k(t(g, i(z(f), u ?? 1e-8)), -d),
+    z(t(f, i(A(g), u ?? 1e-8)), -d),
     r
   );
 }
-const C = {
+const h = {
   kernelName: "AdamAdjust",
   backendName: "cpu",
-  kernelFunc: A
+  kernelFunc: C
 };
-h(C);
+k(h);

package/dist/ops/cpu/adamMoments.js

@@ -1,16 +1,16 @@
-import { h as p } from "../../index-D0RBWjq8.js";
-import { s as b } from "../../stack-WJK22CFn.js";
-function f(t) {
+import { f as p } from "../../index-Duu1Lvvv.js";
+import { s as f } from "../../stack-CDWShFHF.js";
+function b(t) {
   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 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);
+  return f([M, d], -1);
 }
 const g = {
   kernelName: "AdamMoments",
   backendName: "cpu",
-  kernelFunc: f
+  kernelFunc: b
 };
 p(g);

package/dist/ops/cpu/appendCache.js

@@ -1,13 +1,13 @@
-import { h as d } from "../../index-D0RBWjq8.js";
-import { c as m } from "../../concat-C6X3AAlQ.js";
+import { f as d } from "../../index-Duu1Lvvv.js";
+import { c as h } from "../../concat-CSm2rMwe.js";
 function u(p) {
   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]), h = 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 = m([f, r, h], 2);
-    return f.dispose(), h.dispose(), r !== s && r.dispose(), k;
+    const l = 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([l, r, m], 2);
+    return l.dispose(), m.dispose(), r !== s && r.dispose(), k;
   }
-  const l = n.slice([0, 0, e, 0], [t, o, i - e, a]), C = m([l, s], 2);
-  return l.dispose(), C;
+  const f = n.slice([0, 0, e, 0], [t, o, i - e, a]), C = h([f, s], 2);
+  return f.dispose(), C;
 }
 const w = {
   kernelName: "AppendCache",

package/dist/ops/cpu/attentionMask.js

@@ -1,9 +1,9 @@
-import { h as o, i as d, b as u } from "../../index-D0RBWjq8.js";
-import { l as N } from "../../ops-FJapAPfm.js";
-import { o as b } from "../../ones-BX_wEgzB.js";
-import { z as A } from "../../zeros-DeiE2zTa.js";
-import { w as I } from "../../resize_nearest_neighbor-DB8k9KN_.js";
-import { m as g } from "../../mat_mul-DxpNTCRz.js";
+import { f as o, h as d, b as u } from "../../index-Duu1Lvvv.js";
+import { l as N } from "../../ops-C2_OXuZ4.js";
+import { o as b } from "../../ones-CBI1AQjb.js";
+import { z as A } from "../../zeros-5YROwwUH.js";
+import { w as I } from "../../resize_nearest_neighbor-BA_BX-ub.js";
+import { m as g } from "../../mat_mul-Bn2BDpT4.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(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);

package/dist/ops/cpu/fusedSoftmax.js

@@ -1,17 +1,17 @@
-import { h as e } from "../../index-D0RBWjq8.js";
-import { s as m } from "../../softmax-faLoUZVT.js";
+import { f as e } from "../../index-Duu1Lvvv.js";
+import { s as f } from "../../softmax-DfuYyjMh.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(o, i);
+  return r !== void 0 && r > 0 && console.warn("Dropout in fusedSoftmax not implemented for CPU backend, skipping dropout."), f(o, i);
 }
-const f = {
+const m = {
   kernelName: "FusedSoftmax",
   backendName: "cpu",
   kernelFunc: n
 };
-e(f);
+e(m);
 const u = {
   kernelName: "FusedSoftmax",
   backendName: "tensorflow",

package/dist/ops/cpu/gatherSub.js

@@ -1,14 +1,14 @@
-import { q as u, u as c, E as g, aj as h, h as m, c as p } from "../../index-D0RBWjq8.js";
-import { r as l } from "../../range-CuGvVN2c.js";
-import { s as N } from "../../stack-WJK22CFn.js";
-function f(e, t) {
+import { o as u, q as c, E as g, aj as h, f as m, c as p } from "../../index-Duu1Lvvv.js";
+import { r as f } from "../../range-DKmP1-OQ.js";
+import { s as l } from "../../stack-CDWShFHF.js";
+function N(e, t) {
   const n = c(t, "indices", "gatherND", "int32"), s = { params: c(e, "x", "gatherND", "string_or_numeric"), indices: n };
   return g.runKernel(h, s);
 }
-const b = /* @__PURE__ */ u({ gatherND_: f });
+const b = /* @__PURE__ */ u({ gatherND_: N });
 function d(e) {
-  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 p(t, o);
+  const { values: t, labels: n, logits: r } = e.inputs, s = n.shape[0], a = f(0, s, 1, "int32"), o = l([a, n], 1), i = b(r, o);
+  return p(t, i);
 }
 const k = {
   kernelName: "EfficientGatherSub",

package/dist/ops/cpu/gelu.js

@@ -1,4 +1,4 @@
-import { h as t, t as d } from "../../index-D0RBWjq8.js";
+import { f as t, t as d } from "../../index-Duu1Lvvv.js";
 const o = 0.7978845608028654, c = 0.044715;
 function m(r) {
   const { inputs: u } = r, { x: n } = u, e = n;
@@ -26,15 +26,15 @@ function i(r) {
     return u.mul(N);
   });
 }
-const h = {
+const x = {
   kernelName: "GeluGrad",
   backendName: "cpu",
   kernelFunc: i
 };
-t(h);
-const x = {
+t(x);
+const h = {
   kernelName: "GeluGrad",
   backendName: "tensorflow",
   kernelFunc: i
 };
-t(x);
+t(h);

package/dist/ops/cpu/matMul16.js

@@ -1,6 +1,6 @@
 import { isPackedTensor as t } from "../../utilities/packed.js";
-import { h as p } from "../../index-D0RBWjq8.js";
-import { m as l } from "../../mat_mul-DxpNTCRz.js";
+import { f as p } from "../../index-Duu1Lvvv.js";
+import { m as l } from "../../mat_mul-Bn2BDpT4.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)

package/dist/ops/cpu/matMulGelu.js

@@ -1,6 +1,6 @@
-import { h as e, t as m } from "../../index-D0RBWjq8.js";
-import { g as M, d as i } from "../../gelu-DqTbCx5x.js";
-import { m as k } from "../../mat_mul-DxpNTCRz.js";
+import { f as e, t as m } from "../../index-Duu1Lvvv.js";
+import { g as M, d as i } from "../../gelu-BK1k-n1i.js";
+import { m as k } from "../../mat_mul-Bn2BDpT4.js";
 function c(t) {
   const { inputs: u } = t, { x: n, kernel: r } = u, a = n, l = r;
   return m(() => {

package/dist/ops/cpu/matMulMul.js

@@ -1,20 +1,20 @@
-import { h as e, t as i } from "../../index-D0RBWjq8.js";
+import { f as e, t as i } from "../../index-Duu1Lvvv.js";
 function n(t) {
   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 = {
+const f = {
   kernelName: "MatMulMul",
   backendName: "cpu",
   kernelFunc: n
 };
-e(p);
-const f = {
+e(f);
+const p = {
   kernelName: "MatMulMul",
   backendName: "tensorflow",
   kernelFunc: n
 };
-e(f);
+e(p);
 const g = {
   kernelName: "MatMulMul",
   backendName: "webgpu",

package/dist/ops/cpu/mulDropout.js

@@ -1,4 +1,4 @@
-import { h as e, m as t } from "../../index-D0RBWjq8.js";
+import { f as e, m as t } from "../../index-Duu1Lvvv.js";
 function n(o) {
   const { inputs: r } = o, { a: l, b: u } = r;
   return console.warn("Using fallback mulDrop implementation without dropout."), t(l, u);

package/dist/ops/cpu/normRMS.js

@@ -1,4 +1,4 @@
-import { h as o, t as d } from "../../index-D0RBWjq8.js";
+import { f as o, t as d } from "../../index-Duu1Lvvv.js";
 function i(t) {
   const { inputs: e } = t, { x: n, gamma: s } = e, r = n, a = s;
   return d(() => {
@@ -6,12 +6,12 @@ function i(t) {
     return r.mul(u).mul(a);
   });
 }
-const f = {
+const k = {
   kernelName: "RMSNorm",
   backendName: "cpu",
   kernelFunc: i
 };
-o(f);
+o(k);
 const g = {
   kernelName: "RMSNorm",
   backendName: "tensorflow",
@@ -21,8 +21,8 @@ o(g);
 function N(t) {
   const { dy: e, x: n, gamma: s } = t.inputs;
   return d(() => {
-    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 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), f = c.mul(n).sum(-1, !0).div(r);
+    return [c.mul(m).sub(n.mul(f).mul(m).div(a.add(1e-8))), l];
   });
 }
 const S = {

package/dist/ops/cpu/qkv.js

@@ -1,6 +1,6 @@
-import { h as q } from "../../index-D0RBWjq8.js";
-import { r as o } from "../../reshape-CkjKPPqB.js";
-import { s as x } from "../../split-BNz5jcGc.js";
+import { f as q } from "../../index-Duu1Lvvv.js";
+import { r as o } from "../../reshape-BI0yzp1T.js";
+import { s as x } from "../../split-BYrLboMq.js";
 function v(p) {
   const { x: c, kernel: K } = p.inputs, { heads: n, packed: C } = p.attrs;
   if (C)

package/dist/ops/cpu/rope.js

@@ -1,20 +1,20 @@
-import { h as I } from "../../index-D0RBWjq8.js";
-import { r as y } from "../../range-CuGvVN2c.js";
-import { g as F } from "../../gather-BcO5UQNJ.js";
-import { s as E } from "../../stack-WJK22CFn.js";
-import { c as T } from "../../concat-C6X3AAlQ.js";
+import { f as I } from "../../index-Duu1Lvvv.js";
+import { r as y } from "../../range-DKmP1-OQ.js";
+import { g as F } from "../../gather-BSULDalH.js";
+import { s as E } from "../../stack-CDWShFHF.js";
+import { c as T } from "../../concat-CSm2rMwe.js";
 function U(c, r, p, e, n) {
   const t = e.shape[3], s = p;
   if (s > t) return e;
-  const o = e.shape[2], i = s / 2, a = r.slice([n, 0, 0], [o, i, 1]).reshape([1, 1, o, i]), d = c.slice([n, 0, 0], [o, i, 1]).reshape([1, 1, o, i]), l = e.shape[0], m = e.shape[1], f = y(0, s, 2, "int32"), g = y(1, s, 2, "int32"), D = ((k) => {
-    const C = k.slice([0, 0, 0, 0], [l, m, o, s]), R = s < t ? k.slice([0, 0, 0, s], [l, m, o, t - s]) : null, u = F(C, f, 3), h = F(C, g, 3), v = u.mul(a), N = h.mul(d), S = v.sub(N), P = h.mul(a), b = u.mul(d), x = P.add(b);
-    u.dispose(), h.dispose(), a.dispose(), d.dispose(), v.dispose(), N.dispose(), P.dispose(), b.dispose();
+  const o = e.shape[2], i = s / 2, a = r.slice([n, 0, 0], [o, i, 1]).reshape([1, 1, o, i]), d = c.slice([n, 0, 0], [o, i, 1]).reshape([1, 1, o, i]), l = e.shape[0], m = e.shape[1], h = y(0, s, 2, "int32"), g = y(1, s, 2, "int32"), D = ((k) => {
+    const C = k.slice([0, 0, 0, 0], [l, m, o, s]), R = s < t ? k.slice([0, 0, 0, s], [l, m, o, t - s]) : null, u = F(C, h, 3), f = F(C, g, 3), v = u.mul(a), N = f.mul(d), S = v.sub(N), P = f.mul(a), b = u.mul(d), x = P.add(b);
+    u.dispose(), f.dispose(), a.dispose(), d.dispose(), v.dispose(), N.dispose(), P.dispose(), b.dispose();
     const K = E([S, x], -1);
     S.dispose(), x.dispose();
     const w = K.reshape([l, m, o, s]);
     return K.dispose(), R ? T([w, R], 3) : w;
   })(e);
-  return f.dispose(), g.dispose(), D;
+  return h.dispose(), g.dispose(), D;
 }
 function B(c) {
   const { x: r } = c.inputs, { pastLen: p, negSin: e, ropeCache: n } = c.attrs, t = r.shape[3], s = e ? n.getNegSin() : n.getSin(), o = n.getCos();

package/dist/ops/cpu/scatterSub.js

@@ -1,8 +1,8 @@
-import { q as f, w as g, u as r, E as l, ai as N, h as b, c as S, m as h } from "../../index-D0RBWjq8.js";
-import { v as D } from "../../scatter_nd_util-BY22Cc-C.js";
-import { r as k } from "../../range-CuGvVN2c.js";
-import { s as v } from "../../stack-WJK22CFn.js";
-import { o as E } from "../../ones-BX_wEgzB.js";
+import { o as f, u as g, q as r, E as l, ai as N, f as b, c as S, m as h } from "../../index-Duu1Lvvv.js";
+import { v as D } from "../../scatter_nd_util-k9MUVUkn.js";
+import { r as k } from "../../range-DKmP1-OQ.js";
+import { s as v } from "../../stack-CDWShFHF.js";
+import { o as E } from "../../ones-CBI1AQjb.js";
 function I(a, e, s) {
   g(s);
   const n = r(a, "indices", "scatterND", "int32"), t = r(e, "updates", "scatterND");

package/dist/ops/dot16.js

@@ -1,8 +1,8 @@
-import { b as d } from "../matMul16-cDxwemKj.js";
+import { b as d } from "../matMul16-xswmhSuF.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-Vi4JfLzT.js";
+import { d as x } from "../tfjs_backend-806hyYve.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-D0RBWjq8.js";
+import { e as n } from "../index-Duu1Lvvv.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-D0RBWjq8.js";
+import "../index-Duu1Lvvv.js";
 import "./cpu/gelu.js";
 import "./webgl/gelu.js";
-import { d as e, g as i } from "../gelu-DqTbCx5x.js";
+import { d as e, g as i } from "../gelu-BK1k-n1i.js";
 export {
   e as dGelu,
   i as gelu

package/dist/ops/grads/add16.js

@@ -1,4 +1,4 @@
-import { j as u, $ as h, a0 as d } from "../../index-D0RBWjq8.js";
+import { i as u, _ as h, $ as d } from "../../index-Duu1Lvvv.js";
 import { sum16 as c } from "../sum16.js";
 import { reshape16 as p } from "../reshape16.js";
 const A = {

package/dist/ops/grads/attentionMask.js

@@ -1,5 +1,5 @@
-import { j as m } from "../../index-D0RBWjq8.js";
-import { m as o } from "../../matMul16-cDxwemKj.js";
+import { i as m } from "../../index-Duu1Lvvv.js";
+import { m as o } from "../../matMul16-xswmhSuF.js";
 import { transpose16 as c } from "../transpose16.js";
 const l = {
   kernelName: "AttentionMask",

package/dist/ops/grads/gelu.js

@@ -1,5 +1,5 @@
-import "../../index-D0RBWjq8.js";
-import { a as e } from "../../gelu-DqTbCx5x.js";
+import "../../index-Duu1Lvvv.js";
+import { a as e } from "../../gelu-BK1k-n1i.js";
 export {
   e as geluGradConfig
 };

package/dist/ops/grads/matMul16.js

@@ -1,6 +1,6 @@
-import "../../index-D0RBWjq8.js";
-import { a } from "../../matMul16-cDxwemKj.js";
-import "../../gelu-DqTbCx5x.js";
+import "../../index-Duu1Lvvv.js";
+import { a } from "../../matMul16-xswmhSuF.js";
+import "../../gelu-BK1k-n1i.js";
 import "../transpose16.js";
 import "../reshape16.js";
 export {

package/dist/ops/grads/matMulGelu.js

@@ -1,17 +1,17 @@
-import { j as a, e as o } from "../../index-D0RBWjq8.js";
-function s(e, n, r) {
+import { i as a, e as o } from "../../index-Duu1Lvvv.js";
+function i(e, n, r) {
   return o().runKernel("MatMulGeluGrad", { dy: e, x: n, kernel: r });
 }
-const d = {
+const s = {
   kernelName: "MatMulGelu",
   inputsToSave: ["x", "kernel"],
   outputsToSave: [],
   gradFunc: (e, n) => {
-    const [r, t] = n, [u, l] = s(e, r, t);
+    const [r, t] = n, [u, l] = i(e, r, t);
     return {
       x: () => u,
       kernel: () => l
     };
   }
 };
-a(d);
+a(s);

package/dist/ops/grads/normRMS.js

@@ -1,20 +1,20 @@
-import { j as t, e as g } from "../../index-D0RBWjq8.js";
-function s(r, a, n) {
+import { i as t, e as g } from "../../index-Duu1Lvvv.js";
+function i(r, a, n) {
   return g().runKernel("RMSNormGrad", { dy: r, x: a, gamma: n });
 }
-const u = {
+const s = {
   kernelName: "RMSNorm",
   inputsToSave: ["x", "gamma"],
   outputsToSave: [],
   gradFunc: (r, a) => {
-    const [n, e] = a, [m, o] = s(r, n, e);
+    const [n, e] = a, [m, o] = i(r, n, e);
     return {
       x: () => m,
       gamma: () => o
     };
   }
 };
-t(u);
+t(s);
 export {
-  u as normRMSGradConfig
+  s as normRMSGradConfig
 };

package/dist/ops/grads/pack16.js

@@ -1,6 +1,6 @@
-import "../../index-D0RBWjq8.js";
-import { b as i } from "../../pack16-k4jq6aMX.js";
-import "../../slice-Aqy7KbJh.js";
+import "../../index-Duu1Lvvv.js";
+import { b as i } from "../../pack16-atD0eYRm.js";
+import "../../slice-wBNvzVyz.js";
 export {
   i as packGradConfig
 };

package/dist/ops/grads/qkv.js

@@ -1,34 +1,34 @@
-import { j as u } from "../../index-D0RBWjq8.js";
-import { a as f } from "../../matMul16-cDxwemKj.js";
+import { i as u } from "../../index-Duu1Lvvv.js";
+import { a as f } from "../../matMul16-xswmhSuF.js";
 import { concat16 as g } from "../concat16.js";
 import { sum16 as l } from "../sum16.js";
-import { s as k } from "../../squeeze--YMgaAAf.js";
-const i = {
+import { s as k } from "../../squeeze-Bk8Brcct.js";
+const d = {
   kernelName: "QKV",
   inputsToSave: ["x", "kernel"],
   outputsToSave: [],
   gradFunc: (e, s) => {
     const [r, n, t] = e, [a] = s, p = g([r, n, t], 1);
     r.dispose(), n.dispose(), t.dispose();
-    const m = [a.shape[0], a.shape[1], 3 * a.shape[2]], d = f.gradFunc(p, s, {
+    const m = [a.shape[0], a.shape[1], 3 * a.shape[2]], i = f.gradFunc(p, s, {
       transposeA: !1,
       transposeB: !1,
       originalShape: m,
       perm: [0, 2, 1, 3]
     });
     return p.dispose(), {
-      x: () => d.A(),
+      x: () => i.A(),
       kernel: () => {
-        const o = d.B(), c = o.shape[0] === 1 ? k(o, [0]) : l(o, 0);
+        const o = i.B(), c = o.shape[0] === 1 ? k(o, [0]) : l(o, 0);
         return o.dispose(), c;
       }
     };
   }
 };
 function B(e, s, r) {
-  return i.gradFunc(e, [s, r], {});
+  return d.gradFunc(e, [s, r], {});
 }
-u(i);
+u(d);
 export {
   B as qkvGrad
 };

package/dist/ops/grads/rope.js

@@ -1,5 +1,5 @@
-import "../../index-D0RBWjq8.js";
-import { a as p } from "../../rope-BmZmp9uP.js";
+import "../../index-Duu1Lvvv.js";
+import { a as p } from "../../rope-DJ7Y7c-u.js";
 export {
   p as ropeGradConfig
 };

package/dist/ops/grads/softmax16.js

@@ -1,4 +1,4 @@
-import { j as n, e as a } from "../../index-D0RBWjq8.js";
+import { i as n, e as a } from "../../index-Duu1Lvvv.js";
 import { isPackedTensor as t } from "../../utilities/packed.js";
 function s(r, e) {
   return a().runKernel("Softmax16Grad", { dy: r, softmaxOutput: e });

package/dist/ops/grads/unpack16.js

@@ -1,5 +1,5 @@
-import "../../index-D0RBWjq8.js";
-import { a as p } from "../../pack16-k4jq6aMX.js";
+import "../../index-Duu1Lvvv.js";
+import { a as p } from "../../pack16-atD0eYRm.js";
 export {
   p as unpackGradConfig
 };

package/dist/ops/matMul16.js

@@ -1,9 +1,9 @@
-import "../index-D0RBWjq8.js";
-import { b as p, c as u, d as i, e as s, m as M } from "../matMul16-cDxwemKj.js";
+import "../index-Duu1Lvvv.js";
+import { b as p, c as u, d as i, e as s, m as M } from "../matMul16-xswmhSuF.js";
 import "./webgl/matMul16.js";
 import "./cpu/matMul16.js";
 import "../utilities/packed.js";
-import "../pack16-k4jq6aMX.js";
+import "../pack16-atD0eYRm.js";
 export {
   p as matMul16,
   u as matMul16Gelu,

package/dist/ops/matMulGelu.js

@@ -1,6 +1,6 @@
-import { e as u } from "../index-D0RBWjq8.js";
+import { e as u } from "../index-Duu1Lvvv.js";
 import "./cpu/matMulGelu.js";
-import "../matMulGelu-B2s_80-H.js";
+import "../matMulGelu-BpvgnYG8.js";
 import "./grads/matMulGelu.js";
 function M(r, e) {
   return u().runKernel("MatMulGelu", { x: r, kernel: e });

package/dist/ops/matMulMul.js

@@ -1,4 +1,4 @@
-import { e as u } from "../index-D0RBWjq8.js";
+import { e as u } from "../index-Duu1Lvvv.js";
 import "./cpu/matMulMul.js";
 import "./webgl/matMulMul.js";
 function m(e, r, t, l = !1, n = !1) {

package/dist/ops/mul16.js

@@ -1,4 +1,4 @@
-import { m as t, e as u } from "../index-D0RBWjq8.js";
+import { m as t, e as u } from "../index-Duu1Lvvv.js";
 import { isPackedTensor as n } from "../utilities/packed.js";
 function i(r, e) {
   return !n(r) && !n(e) ? t(r, e) : u().runKernel("Mul16", { a: r, b: e });

package/dist/ops/mulDrop.js

@@ -1,4 +1,4 @@
-import { e as t } from "../index-D0RBWjq8.js";
+import { e as t } from "../index-Duu1Lvvv.js";
 import "./cpu/mulDropout.js";
 import "./webgl/mulDropout.js";
 function m(r, o, e, n) {

package/dist/ops/normRMS.js

@@ -1,4 +1,4 @@
-import { e as n } from "../index-D0RBWjq8.js";
+import { e as n } from "../index-Duu1Lvvv.js";
 import "./cpu/normRMS.js";
 import "./webgl/normRMS.js";
 import "./grads/normRMS.js";

package/dist/ops/pack16.js

@@ -1,5 +1,5 @@
-import "../index-D0RBWjq8.js";
-import { p as a } from "../pack16-k4jq6aMX.js";
+import "../index-Duu1Lvvv.js";
+import { p as a } from "../pack16-atD0eYRm.js";
 export {
   a as pack16
 };

package/dist/ops/qkv.js

@@ -1,4 +1,4 @@
-import { e as t } from "../index-D0RBWjq8.js";
+import { e as t } from "../index-Duu1Lvvv.js";
 import "./cpu/qkv.js";
 import "./webgl/qkv.js";
 import "./grads/qkv.js";