Commit d7d1b632d for llama.cpp

commit d7d1b632da766f1247456b4f42406a96a0609d93
Author: Nikhil Jain <nikhil.jain0987@gmail.com>
Date:   Thu Nov 19 23:45:44 2026 -0800

    webgpu : fix 2D indexing for copy kernel (#32576)

    * Only run webgpu CI on my fork

    * Add webgpu only workflow

    * resolve merge conflicts

    * Add 2d indexing to copy kernel

    * move test

diff --git a/ggml/src/ggml-webgpu/wgsl-shaders/cpy.wgsl b/ggml/src/ggml-webgpu/wgsl-shaders/cpy.wgsl
index 0d0d81ab6..2466b2f0b 100644
--- a/ggml/src/ggml-webgpu/wgsl-shaders/cpy.wgsl
+++ b/ggml/src/ggml-webgpu/wgsl-shaders/cpy.wgsl
@@ -53,12 +53,14 @@ var<uniform> params: Params;
 @compute @workgroup_size(WG_SIZE)
 fn main(
     @builtin(global_invocation_id) gid: vec3<u32>,
+    @builtin(num_workgroups) num_wg: vec3<u32>,
 ) {
-    if (gid.x >= params.ne) {
+    let idx = gid.x + num_wg.x * WG_SIZE * gid.y;
+    if (idx >= params.ne) {
         return;
     }

-    var i = gid.x;
+    var i = idx;
     let i3 = i / (params.src_ne2 * params.src_ne1 * params.src_ne0);
     i = i % (params.src_ne2 * params.src_ne1 * params.src_ne0);
     let i2 = i / (params.src_ne1 * params.src_ne0);
@@ -66,7 +68,7 @@ fn main(
     let i1 = i / params.src_ne0;
     let i0 = i % params.src_ne0;

-    var j = gid.x;
+    var j = idx;
     let j3 = j / (params.dst_ne2 * params.dst_ne1 * params.dst_ne0);
     j = j % (params.dst_ne2 * params.dst_ne1 * params.dst_ne0);
     let j2 = j / (params.dst_ne1 * params.dst_ne0);
diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp
index f75d93bc3..42e356ae0 100644
--- a/tests/test-backend-ops.cpp
+++ b/tests/test-backend-ops.cpp
@@ -11507,7 +11507,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
     test_cases.emplace_back(new test_cpy(GGML_TYPE_F16, GGML_TYPE_F16, {128, 2, 3, 1}, {128, 2, 3, 1}, {0, 0, 0, 0}, {0, 0, 0, 0}, false, {128, 4, 3, 1})); // strided dst
     test_cases.emplace_back(new test_cpy(GGML_TYPE_F32, GGML_TYPE_F32, {64, 16, 1, 1}, {1, 64, 16, 1}, {1, 2, 0, 3}, {0, 0, 0, 0}, false, {32, 64, 16, 1})); // permuted src, strided dst
     test_cases.emplace_back(new test_cpy(GGML_TYPE_F16, GGML_TYPE_F16, {64, 16, 1, 1}, {1, 64, 16, 1}, {1, 2, 0, 3}, {0, 0, 0, 0}, false, {32, 64, 16, 1})); // permuted src, strided dst
-
+    test_cases.emplace_back(new test_cpy(GGML_TYPE_F32, GGML_TYPE_F32, {2, 2, 524281, 1}, {-1,-1,-1,-1}, {1, 0, 2, 3}));
     // CPY - different src/dst shapes (reshaping via CPY)
     // Use permutations of {3, 5, 7, 32}. Total elements: 3*5*7*32 = 3360.
     // Each src permutation is tested against canonical sorted and reverse dst (skip self).