From d2396e4e3630e766353c8f8832e324795ba708f7 Mon Sep 17 00:00:00 2001 From: Revertron Date: Sat, 21 Nov 2026 14:11:24 +0100 Subject: [PATCH] upstream-carry #32735: vulkan : support non-contiguous src in SCALE Temporary carry of the open upstream PR https://github.com/ggml-org/llama.cpp/pull/32735 (head 0ea4ffd00), cherry-picked unchanged. The Vulkan backend runs SCALE on a non-contiguous source instead of rejecting it (CPU fallback). Carried together with #32740 and evaluated as a pair. Drop this commit when the PR is merged upstream (FORK.md, "Temporary upstream carries"). Original commit trailer: Assisted-By: Opus 5.5 Co-Authored-By: Claude Opus 5.5 Claude-Session: https://claude.ai/code/session_01PZz44SLQvTXMyWGio6t9DZ --- ggml/src/ggml-vulkan/ggml-vulkan.cpp | 2 +- ggml/src/ggml-vulkan/vulkan-shaders/scale.comp | 2 +- tests/test-backend-ops.cpp | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp index 483141fd2..2cba63ee5 100644 --- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp +++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp @@ -17207,7 +17207,7 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm case GGML_OP_SLEEP: return device->shader_clock; case GGML_OP_SCALE: - return ggml_is_contiguous(op->src[0]) && ggml_vk_is_float_elementwise(op); + return ggml_vk_is_float_elementwise(op); case GGML_OP_PAD: case GGML_OP_PAD_REFLECT_1D: case GGML_OP_ROLL: diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/scale.comp b/ggml/src/ggml-vulkan/vulkan-shaders/scale.comp index 83ee31a72..0313f2fed 100644 --- a/ggml/src/ggml-vulkan/vulkan-shaders/scale.comp +++ b/ggml/src/ggml-vulkan/vulkan-shaders/scale.comp @@ -18,7 +18,7 @@ void main() { continue; } - data_d[get_doffset() + idx] = FLOAT_TO_D(A_TO_FLOAT(data_a[get_aoffset() + idx]) * FLOAT_TYPE(p.param1) + FLOAT_TYPE(p.param2)); + data_d[get_doffset() + dst_idx(idx)] = FLOAT_TO_D(A_TO_FLOAT(data_a[get_aoffset() + src0_idx(idx)]) * FLOAT_TYPE(p.param1) + FLOAT_TYPE(p.param2)); idx += num_threads; } } diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp index e377277a4..9b8d7015c 100644 --- a/tests/test-backend-ops.cpp +++ b/tests/test-backend-ops.cpp @@ -11758,6 +11758,7 @@ static std::vector> make_test_cases_eval() { test_cases.emplace_back(new test_scale(GGML_TYPE_F32, {10, 10, 10, 10}, 2.0f, 1.0f, false, 1)); // view test test_cases.emplace_back(new test_scale(GGML_TYPE_F32, {10, 10, 10, 10}, 2.0f, 1.0f, true, 1)); // view test, inplace test_cases.emplace_back(new test_scale(GGML_TYPE_BF16, {10, 10, 10, 10}, 2.0f, 1.0f, true, 1)); // view test, inplace + test_cases.emplace_back(new test_scale(GGML_TYPE_F16, {10, 10, 10, 10}, 2.0f, 1.0f, false, 1)); // view test test_cases.emplace_back(new test_softcap(GGML_TYPE_F32, {10, 10, 10, 10}, 50.0f)); test_cases.emplace_back(new test_silu_back());