Commit ede610678 for llama.cpp

commit ede6106780fef959e40ae309afb68da7b6442883
Author: lhez <lih@qti.qualcomm.com>
Date:   Tue Nov 17 00:38:07 2026 -0800

    opencl: support f16 and non-contig f32 silu (#32319)

    * opencl: support non-contig silu

    Assisted-by: Claude Opus 5.5

    * opencl: support f16 silu

    Assisted-by: Claude Opus 5.5

diff --git a/docs/ops/OpenCL.csv b/docs/ops/OpenCL.csv
index 8b595e4b9..e5f2bbd0c 100644
--- a/docs/ops/OpenCL.csv
+++ b/docs/ops/OpenCL.csv
@@ -19,8 +19,8 @@
 "OpenCL","GELU","type=f16,ne_a=[5,7,11,13],v=0","support","0","no","OpenCL"
 "OpenCL","GELU_QUICK","type=f16,ne_a=[128,2,2,2],v=0","support","0","no","OpenCL"
 "OpenCL","GELU_QUICK","type=f16,ne_a=[5,7,11,13],v=0","support","0","no","OpenCL"
-"OpenCL","SILU","type=f16,ne_a=[128,2,2,2],v=0","support","0","no","OpenCL"
-"OpenCL","SILU","type=f16,ne_a=[5,7,11,13],v=0","support","0","no","OpenCL"
+"OpenCL","SILU","type=f16,ne_a=[128,2,2,2],v=0","support","1","yes","OpenCL"
+"OpenCL","SILU","type=f16,ne_a=[5,7,11,13],v=0","support","1","yes","OpenCL"
 "OpenCL","HARDSWISH","type=f16,ne_a=[128,2,2,2],v=0","support","1","yes","OpenCL"
 "OpenCL","HARDSWISH","type=f16,ne_a=[5,7,11,13],v=0","support","1","yes","OpenCL"
 "OpenCL","HARDSIGMOID","type=f16,ne_a=[128,2,2,2],v=0","support","1","yes","OpenCL"
@@ -61,8 +61,8 @@
 "OpenCL","GELU","type=f16,ne_a=[5,7,11,13],v=1","support","0","no","OpenCL"
 "OpenCL","GELU_QUICK","type=f16,ne_a=[128,2,2,2],v=1","support","0","no","OpenCL"
 "OpenCL","GELU_QUICK","type=f16,ne_a=[5,7,11,13],v=1","support","0","no","OpenCL"
-"OpenCL","SILU","type=f16,ne_a=[128,2,2,2],v=1","support","0","no","OpenCL"
-"OpenCL","SILU","type=f16,ne_a=[5,7,11,13],v=1","support","0","no","OpenCL"
+"OpenCL","SILU","type=f16,ne_a=[128,2,2,2],v=1","support","1","yes","OpenCL"
+"OpenCL","SILU","type=f16,ne_a=[5,7,11,13],v=1","support","1","yes","OpenCL"
 "OpenCL","HARDSWISH","type=f16,ne_a=[128,2,2,2],v=1","support","1","yes","OpenCL"
 "OpenCL","HARDSWISH","type=f16,ne_a=[5,7,11,13],v=1","support","1","yes","OpenCL"
 "OpenCL","HARDSIGMOID","type=f16,ne_a=[128,2,2,2],v=1","support","1","yes","OpenCL"
@@ -145,8 +145,8 @@
 "OpenCL","GELU","type=f32,ne_a=[5,7,11,13],v=1","support","0","no","OpenCL"
 "OpenCL","GELU_QUICK","type=f32,ne_a=[128,2,2,2],v=1","support","0","no","OpenCL"
 "OpenCL","GELU_QUICK","type=f32,ne_a=[5,7,11,13],v=1","support","0","no","OpenCL"
-"OpenCL","SILU","type=f32,ne_a=[128,2,2,2],v=1","support","0","no","OpenCL"
-"OpenCL","SILU","type=f32,ne_a=[5,7,11,13],v=1","support","0","no","OpenCL"
+"OpenCL","SILU","type=f32,ne_a=[128,2,2,2],v=1","support","1","yes","OpenCL"
+"OpenCL","SILU","type=f32,ne_a=[5,7,11,13],v=1","support","1","yes","OpenCL"
 "OpenCL","HARDSWISH","type=f32,ne_a=[128,2,2,2],v=1","support","1","yes","OpenCL"
 "OpenCL","HARDSWISH","type=f32,ne_a=[5,7,11,13],v=1","support","1","yes","OpenCL"
 "OpenCL","HARDSIGMOID","type=f32,ne_a=[128,2,2,2],v=1","support","1","yes","OpenCL"
diff --git a/ggml/src/ggml-opencl/ggml-opencl.cpp b/ggml/src/ggml-opencl/ggml-opencl.cpp
index d53880375..0ff9764f0 100644
--- a/ggml/src/ggml-opencl/ggml-opencl.cpp
+++ b/ggml/src/ggml-opencl/ggml-opencl.cpp
@@ -869,7 +869,8 @@ struct ggml_backend_opencl_context {
     cl_kernel kernel_sqr_cont_f32, kernel_sqr_cont_f32_4, kernel_sqr_cont_f16, kernel_sqr_cont_f16_4;
     cl_kernel kernel_sqrt_cont_f32, kernel_sqrt_cont_f32_4, kernel_sqrt_cont_f16, kernel_sqrt_cont_f16_4;
     cl_kernel kernel_mean_f32, kernel_mean_f32_4;
-    cl_kernel kernel_silu, kernel_silu_4;
+    cl_kernel kernel_silu, kernel_silu_4, kernel_silu_nc;
+    cl_kernel kernel_silu_f16, kernel_silu_f16_4, kernel_silu_f16_nc;
     cl_kernel kernel_gelu, kernel_gelu_4;
     cl_kernel kernel_gelu_erf, kernel_gelu_erf_4;
     cl_kernel kernel_gelu_quick, kernel_gelu_quick_4;
@@ -4154,6 +4155,10 @@ static void load_cl_kernels(ggml_backend_opencl_context *backend_ctx) {

         CL_CHECK((backend_ctx->kernel_silu   = clCreateKernel(backend_ctx->program_silu, "kernel_silu", &err), err));
         CL_CHECK((backend_ctx->kernel_silu_4 = clCreateKernel(backend_ctx->program_silu, "kernel_silu_4", &err), err));
+        CL_CHECK((backend_ctx->kernel_silu_nc = clCreateKernel(backend_ctx->program_silu, "kernel_silu_nc", &err), err));
+        CL_CHECK((backend_ctx->kernel_silu_f16    = clCreateKernel(backend_ctx->program_silu, "kernel_silu_f16", &err), err));
+        CL_CHECK((backend_ctx->kernel_silu_f16_4  = clCreateKernel(backend_ctx->program_silu, "kernel_silu_f16_4", &err), err));
+        CL_CHECK((backend_ctx->kernel_silu_f16_nc = clCreateKernel(backend_ctx->program_silu, "kernel_silu_f16_nc", &err), err));
         GGML_LOG_CONT(".");
     }

@@ -11977,8 +11982,10 @@ static bool ggml_opencl_supports_op(ggml_backend_dev_t dev, const struct ggml_te
                     ggml_is_contiguous(op->src[0]);
         case GGML_OP_UNARY:
             switch (ggml_get_unary_op(op)) {
-                case GGML_UNARY_OP_GELU:
                 case GGML_UNARY_OP_SILU:
+                    return op->src[0]->type == op->type &&
+                           (op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_F16);
+                case GGML_UNARY_OP_GELU:
                 case GGML_UNARY_OP_RELU:
                 case GGML_UNARY_OP_GELU_ERF:
                 case GGML_UNARY_OP_GELU_QUICK:
@@ -19632,15 +19639,42 @@ static void ggml_cl_silu(ggml_backend_t backend, const ggml_tensor * src0, const
     cl_ulong offset0 = extra0->offset + src0->view_offs;
     cl_ulong offsetd = extrad->offset + dst->view_offs;

+    if (!ggml_is_contiguous(src0) || !ggml_is_contiguous(dst)) {
+        GGML_TENSOR_LOCALS(int,      ne0, src0, ne);
+        GGML_TENSOR_LOCALS(cl_ulong, nb0, src0, nb);
+        GGML_TENSOR_LOCALS(cl_ulong, nb,  dst,  nb);
+
+        cl_kernel kernel = src0->type == GGML_TYPE_F32 ? backend_ctx->kernel_silu_nc : backend_ctx->kernel_silu_f16_nc;
+
+        CL_CHECK(clSetKernelArg(kernel,  0, sizeof(cl_mem),   &extra0->data_device));
+        CL_CHECK(clSetKernelArg(kernel,  1, sizeof(cl_ulong), &offset0));
+        CL_CHECK(clSetKernelArg(kernel,  2, sizeof(cl_mem),   &extrad->data_device));
+        CL_CHECK(clSetKernelArg(kernel,  3, sizeof(cl_ulong), &offsetd));
+        CL_CHECK(clSetKernelArg(kernel,  4, sizeof(int),      &ne00));
+        CL_CHECK(clSetKernelArg(kernel,  5, sizeof(cl_ulong), &nb00));
+        CL_CHECK(clSetKernelArg(kernel,  6, sizeof(cl_ulong), &nb01));
+        CL_CHECK(clSetKernelArg(kernel,  7, sizeof(cl_ulong), &nb02));
+        CL_CHECK(clSetKernelArg(kernel,  8, sizeof(cl_ulong), &nb03));
+        CL_CHECK(clSetKernelArg(kernel,  9, sizeof(cl_ulong), &nb0));
+        CL_CHECK(clSetKernelArg(kernel, 10, sizeof(cl_ulong), &nb1));
+        CL_CHECK(clSetKernelArg(kernel, 11, sizeof(cl_ulong), &nb2));
+        CL_CHECK(clSetKernelArg(kernel, 12, sizeof(cl_ulong), &nb3));
+
+        size_t global_work_size[] = {(size_t)ne01 * 64, (size_t)ne02, (size_t)ne03};
+        size_t local_work_size[] = {64, 1, 1};
+        backend_ctx->enqueue_ndrange_kernel(kernel, 3, global_work_size, local_work_size, dst);
+        return;
+    }
+
     cl_kernel kernel;

     int n = ggml_nelements(dst);

     if (n % 4 == 0) {
-        kernel = backend_ctx->kernel_silu_4;
+        kernel = src0->type == GGML_TYPE_F32 ? backend_ctx->kernel_silu_4 : backend_ctx->kernel_silu_f16_4;
         n /= 4;
     } else {
-        kernel = backend_ctx->kernel_silu;
+        kernel = src0->type == GGML_TYPE_F32 ? backend_ctx->kernel_silu : backend_ctx->kernel_silu_f16;
     }

     CL_CHECK(clSetKernelArg(kernel, 0, sizeof(cl_mem),   &extra0->data_device));
diff --git a/ggml/src/ggml-opencl/kernels/silu.cl b/ggml/src/ggml-opencl/kernels/silu.cl
index 1d95e1b50..a771f3752 100644
--- a/ggml/src/ggml-opencl/kernels/silu.cl
+++ b/ggml/src/ggml-opencl/kernels/silu.cl
@@ -28,3 +28,88 @@ kernel void kernel_silu_4(
     float4 x = src0[get_global_id(0)];
     dst[get_global_id(0)] = x / (1.0f + exp(-x));
 }
+
+kernel void kernel_silu_nc(
+        global const char * src0,
+        ulong               offset0,
+        global       char * dst,
+        ulong               offsetd,
+        int   ne00,
+        ulong nb00,
+        ulong nb01,
+        ulong nb02,
+        ulong nb03,
+        ulong nb0,
+        ulong nb1,
+        ulong nb2,
+        ulong nb3
+) {
+    src0 = src0 + offset0;
+    dst  = dst + offsetd;
+
+    const int i3 = get_group_id(2);
+    const int i2 = get_group_id(1);
+    const int i1 = get_group_id(0);
+
+    for (int i0 = get_local_id(0); i0 < ne00; i0 += get_local_size(0)) {
+        global const float * x = (global const float *)(src0 + i3*nb03 + i2*nb02 + i1*nb01 + i0*nb00);
+        global       float * y = (global       float *)(dst  + i3*nb3  + i2*nb2  + i1*nb1  + i0*nb0);
+
+        *y = *x / (1.0f + exp(-*x));
+    }
+}
+
+kernel void kernel_silu_f16(
+        global half * src0,
+        ulong offset0,
+        global half * dst,
+        ulong offsetd
+) {
+    src0 = (global half*)((global char*)src0 + offset0);
+    dst = (global half*)((global char*)dst + offsetd);
+
+    float x = src0[get_global_id(0)];
+    dst[get_global_id(0)] = x / (1.0f + exp(-x));
+}
+
+kernel void kernel_silu_f16_4(
+        global half4 * src0,
+        ulong offset0,
+        global half4 * dst,
+        ulong offsetd
+) {
+    src0 = (global half4*)((global char*)src0 + offset0);
+    dst = (global half4*)((global char*)dst + offsetd);
+
+    float4 x = convert_float4(src0[get_global_id(0)]);
+    dst[get_global_id(0)] = convert_half4(x / (1.0f + exp(-x)));
+}
+
+kernel void kernel_silu_f16_nc(
+        global const char * src0,
+        ulong               offset0,
+        global       char * dst,
+        ulong               offsetd,
+        int   ne00,
+        ulong nb00,
+        ulong nb01,
+        ulong nb02,
+        ulong nb03,
+        ulong nb0,
+        ulong nb1,
+        ulong nb2,
+        ulong nb3
+) {
+    src0 = src0 + offset0;
+    dst  = dst + offsetd;
+
+    const int i3 = get_group_id(2);
+    const int i2 = get_group_id(1);
+    const int i1 = get_group_id(0);
+
+    for (int i0 = get_local_id(0); i0 < ne00; i0 += get_local_size(0)) {
+        float x = *(global const half *)(src0 + i3*nb03 + i2*nb02 + i1*nb01 + i0*nb00);
+
+        *(global half *)(dst + i3*nb3 + i2*nb2 + i1*nb1 + i0*nb0) = x / (1.0f + exp(-x));
+    }
+}