whispercpp 1.3.4 → 1.3.6

data/ext/sources/ggml/src/ggml-sycl/CMakeLists.txt

@@ -1,7 +1,7 @@
 message(STATUS  "GGML_SYCL_TARGET=${GGML_SYCL_TARGET}")
 
-if (NOT GGML_SYCL_TARGET MATCHES "^(INTEL|NVIDIA|AMD)$")
-    message(FATAL_ERROR "Invalid backend chosen, supported options are INTEL, NVIDIA, or AMD")
+if (NOT GGML_SYCL_TARGET MATCHES "^(INTEL)$")
+    message(FATAL_ERROR "GGML_SYCL_TARGET: Invalid target, the supported options are [INTEL]")
 endif()
 
 check_cxx_compiler_flag("-fsycl" SUPPORTS_SYCL)
@@ -25,6 +25,11 @@ ggml_add_backend_library(ggml-sycl
 
 file(GLOB   GGML_HEADERS_SYCL "*.hpp")
 file(GLOB   GGML_SOURCES_SYCL "*.cpp")
+file(GLOB   SRCS "template-instances/fattn-tile*.cpp")
+list(APPEND GGML_SOURCES_SYCL ${SRCS})
+file(GLOB   SRCS "template-instances/fattn-vec*.cpp")
+list(APPEND GGML_SOURCES_SYCL ${SRCS})
+
 target_sources(ggml-sycl PRIVATE ${GGML_HEADERS_SYCL} ${GGML_SOURCES_SYCL})
 
 if (WIN32)
@@ -36,7 +41,47 @@ if (WIN32)
     endif()
 endif()
 
-find_package(IntelSYCL)
+macro(detect_and_find_package package_name)
+    set(test_source "
+    cmake_minimum_required(VERSION ${CMAKE_VERSION})
+    project(check_package LANGUAGES CXX)
+    find_package(${package_name} QUIET)
+    ")
+
+    set(test_dir "${CMAKE_CURRENT_BINARY_DIR}/check_package_${package_name}")
+    file(WRITE "${test_dir}/CMakeLists.txt" "${test_source}")
+
+    set(cmake_args "")
+    if(CMAKE_GENERATOR)
+        list(APPEND cmake_args "-G" "${CMAKE_GENERATOR}")
+    endif()
+    if(CMAKE_GENERATOR_PLATFORM)
+        list(APPEND cmake_args "-A" "${CMAKE_GENERATOR_PLATFORM}")
+    endif()
+    if(CMAKE_GENERATOR_TOOLSET)
+        list(APPEND cmake_args "-T" "${CMAKE_GENERATOR_TOOLSET}")
+    endif()
+    if(CMAKE_CXX_COMPILER)
+        list(APPEND cmake_args "-DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}")
+    endif()
+
+    execute_process(
+        COMMAND ${CMAKE_COMMAND} ${cmake_args} .
+        WORKING_DIRECTORY "${test_dir}"
+        RESULT_VARIABLE result
+        OUTPUT_QUIET
+        ERROR_QUIET
+    )
+
+    if(result EQUAL 0)
+        find_package(${package_name} ${ARGN})
+    else()
+        message(WARNING "Detection of ${package_name} failed. The package might be broken or incompatible.")
+        set(${package_name}_FOUND FALSE)
+    endif()
+endmacro()
+
+detect_and_find_package(IntelSYCL)
 if (IntelSYCL_FOUND)
     # Use oneAPI CMake when possible
     target_link_libraries(ggml-sycl PRIVATE IntelSYCL::SYCL_CXX)
@@ -85,105 +130,32 @@ endif()
 target_compile_definitions(ggml-sycl PRIVATE GGML_SYCL_DNNL=${GGML_SYCL_DNNL})
 
 if (GGML_SYCL_F16)
-    if (GGML_SYCL_TARGET STREQUAL "AMD")
-        message(WARNING "AMD target does not entirely support FP16 in the SYCL backend.")
-    endif()
     add_compile_definitions(GGML_SYCL_F16)
 endif()
 
-if (GGML_SYCL_TARGET STREQUAL "NVIDIA")
-    add_compile_definitions(GGML_SYCL_WARP_SIZE=32)
-elseif (GGML_SYCL_TARGET STREQUAL "AMD")
-    # INFO: Allowed Sub_group_sizes are not consistent through all
-    # hip targets. For example, 64 is used for certain models, but the backend
-    # does not support it.
-    # Target archs tested working: gfx1030, gfx1031, (Only tested sub_group_size = 32)
-    add_compile_definitions(GGML_SYCL_WARP_SIZE=32)
-else()
+if (GGML_SYCL_TARGET STREQUAL "INTEL")
     add_compile_definitions(GGML_SYCL_WARP_SIZE=16)
-endif()
+    target_link_options(ggml-sycl PRIVATE  -Xs   -ze-intel-greater-than-4GB-buffer-required)
 
-if (GGML_SYCL_GRAPH)
-    target_compile_definitions(ggml-sycl PRIVATE GGML_SYCL_GRAPH)
-endif()
-
-# Link against Intel oneMKL or oneMath
-if (GGML_SYCL_TARGET STREQUAL "INTEL")
-    # Intel devices use Intel oneMKL directly instead of oneMath to avoid the limitation of linking Intel oneMKL statically
-    # See https://github.com/uxlfoundation/oneMath/issues/654
+    # Link against Intel oneMKL
     if (CMAKE_CXX_COMPILER_ID STREQUAL "Clang")
         set(SYCL_COMPILER ON)
     endif()
     find_package(MKL REQUIRED)
     target_link_libraries(ggml-sycl PRIVATE MKL::MKL_SYCL::BLAS)
-    target_compile_definitions(ggml-sycl PRIVATE GGML_SYCL_USE_INTEL_ONEMKL)
 else()
-    find_package(oneMath QUIET)
-    if (NOT oneMath_FOUND)
-        message(STATUS "oneMath not found: oneMath will be automatically downloaded")
-        # Use FetchContent to automatically pull and build oneMath
-        include(FetchContent)
-        set(BUILD_FUNCTIONAL_TESTS False)
-        set(BUILD_EXAMPLES False)
-        set(TARGET_DOMAINS blas)
-        if (GGML_SYCL_TARGET STREQUAL "NVIDIA")
-            set(ENABLE_MKLCPU_BACKEND False)
-            set(ENABLE_MKLGPU_BACKEND False)
-            set(ENABLE_CUBLAS_BACKEND True)
-        elseif (GGML_SYCL_TARGET STREQUAL "AMD")
-            set(ENABLE_MKLCPU_BACKEND False)
-            set(ENABLE_MKLGPU_BACKEND False)
-            set(ENABLE_ROCBLAS_BACKEND True)
-            # Ensure setting a string variable here is not overriden by oneMath CACHE variables
-            cmake_policy(SET CMP0126 NEW)
-            # Setting the device architecture is only needed and useful for AMD devices in oneMath
-            set(HIP_TARGETS ${GGML_SYCL_DEVICE_ARCH} CACHE STRING "oneMath HIP target" FORCE)
-        endif()
-        FetchContent_Declare(
-            ONEMATH
-            GIT_REPOSITORY https://github.com/uxlfoundation/oneMath.git
-            GIT_TAG 8efe85f5aaebb37f1d8c503b7af66315feabf142
-        )
-        FetchContent_MakeAvailable(ONEMATH)
-        # Create alias to match with find_package targets name
-        function(onemath_alias target)
-            if (TARGET ${target}_obj)
-                # Silence verbose warnings from external libraries
-                target_compile_options(${target}_obj PRIVATE -w)
-            endif()
-            if (TARGET ${target})
-                add_library(ONEMATH::${target} ALIAS ${target})
-            endif()
-        endfunction()
-        onemath_alias(onemath)
-        onemath_alias(onemath_blas_mklcpu)
-        onemath_alias(onemath_blas_mklgpu)
-        onemath_alias(onemath_blas_cublas)
-        onemath_alias(onemath_blas_rocblas)
-    endif()
+    # default for other target
+    message(FATAL_ERROR "GGML_SYCL_TARGET is not supported")
+    add_compile_definitions(GGML_SYCL_WARP_SIZE=32)
+endif()
 
-    # Below oneMath compile-time dispatching is used for better performance
-    if (GGML_SYCL_TARGET STREQUAL "NVIDIA")
-        target_link_libraries(ggml-sycl PRIVATE ONEMATH::onemath_blas_cublas)
-        target_compile_options(ggml-sycl PRIVATE "-fsycl-targets=nvptx64-nvidia-cuda")
-        target_link_options(ggml-sycl PRIVATE "-fsycl-targets=nvptx64-nvidia-cuda")
-        target_compile_definitions(ggml-sycl PRIVATE GGML_SYCL_NVIDIA)
-    elseif (GGML_SYCL_TARGET STREQUAL "AMD")
-        if (NOT GGML_SYCL_DEVICE_ARCH)
-            message(FATAL_ERROR "Can't enable SYCL hip backend, GGML_SYCL_DEVICE_ARCH has not been set.")
-        endif()
-        target_link_libraries(ggml-sycl PRIVATE ONEMATH::onemath_blas_rocblas)
-        target_compile_options(ggml-sycl PRIVATE "-fsycl-targets=amdgcn-amd-amdhsa")
-        target_link_options(ggml-sycl PRIVATE "-fsycl-targets=amdgcn-amd-amdhsa")
-        target_compile_definitions(ggml-sycl PRIVATE GGML_SYCL_AMD)
-    else()
-        # Fallback to oneMath runtime dispatcher
-        target_link_libraries(ggml-sycl PRIVATE ONEMATH::onemath)
-        target_compile_definitions(ggml-sycl PRIVATE GGML_SYCL_GENERIC)
-    endif()
+if (GGML_SYCL_GRAPH)
+    message(STATUS "find GGML_SYCL_GRAPH")
+    target_compile_definitions(ggml-sycl PRIVATE GGML_SYCL_GRAPH)
 endif()
 
 if (GGML_SYCL_DEVICE_ARCH)
     target_compile_options(ggml-sycl PRIVATE -Xsycl-target-backend --offload-arch=${GGML_SYCL_DEVICE_ARCH})
     target_link_options(ggml-sycl PRIVATE -Xsycl-target-backend --offload-arch=${GGML_SYCL_DEVICE_ARCH})
 endif()
+

data/ext/sources/ggml/src/ggml-sycl/add-id.cpp

@@ -0,0 +1,81 @@
+#include <sycl/sycl.hpp>
+#include "common.hpp"
+#include "add-id.hpp"
+
+static void add_id_kernel(
+    const float* src0,
+    const float* src1,
+    const int32_t* src2,
+    float* dst,
+    int64_t ne0,
+    int64_t ne1,
+    size_t nb01,
+    size_t nb02,
+    size_t nb11,
+    size_t nb21,
+    sycl::nd_item<3> item_ct1) {
+  const int64_t i1 = item_ct1.get_group(2);
+  const int64_t i2 = item_ct1.get_group(1);
+
+  const int i11 =
+      *(const int32_t*)((const char*)src2 + i1 * sizeof(int32_t) + i2 * nb21);
+
+  const size_t nb1 = ne0 * sizeof(float);
+  const size_t nb2 = ne1 * nb1;
+
+  float* dst_row = (float*)((char*)dst + i1 * nb1 + i2 * nb2);
+  const float* src0_row =
+      (const float*)((const char*)src0 + i1 * nb01 + i2 * nb02);
+  const float* src1_row = (const float*)((const char*)src1 + i11 * nb11);
+
+  for (int64_t i0 = item_ct1.get_local_id(2); i0 < ne0;
+       i0 += item_ct1.get_local_range(2)) {
+    dst_row[i0] = src0_row[i0] + src1_row[i0];
+  }
+}
+
+void ggml_sycl_add_id(ggml_backend_sycl_context& ctx, ggml_tensor* dst) {
+  const ggml_tensor* src0 = dst->src[0];
+  const ggml_tensor* src1 = dst->src[1];
+  const ggml_tensor* src2 = dst->src[2];
+
+  GGML_TENSOR_TERNARY_OP_LOCALS
+
+  GGML_ASSERT(dst->type == GGML_TYPE_F32);
+  GGML_ASSERT(src0->type == GGML_TYPE_F32);
+  GGML_ASSERT(src1->type == GGML_TYPE_F32);
+  GGML_ASSERT(src2->type == GGML_TYPE_I32);
+
+  GGML_ASSERT(nb00 == sizeof(float));
+  GGML_ASSERT(nb10 == sizeof(float));
+  GGML_ASSERT(nb20 == sizeof(int32_t));
+
+  const float* src0_d = (const float*)src0->data;
+  const float* src1_d = (const float*)src1->data;
+  const int32_t* src2_d = (const int32_t*)src2->data;
+  float* dst_d = (float*)dst->data;
+
+  const unsigned int max_work_group_size = ggml_sycl_info().max_work_group_sizes[ctx.device];
+  assert(work_group_size % (WARP_SIZE * WARP_SIZE) == 0);
+
+  int threads = std::min((unsigned int)ne00, max_work_group_size);  // cols
+
+  ctx.stream()->parallel_for(
+      sycl::nd_range<3>(
+          sycl::range<3>(1, ne02, ne01) * sycl::range<3>(1, 1, threads),
+          sycl::range<3>(1, 1, threads)),
+      [=](sycl::nd_item<3> item_ct1) {
+        add_id_kernel(
+            src0_d,
+            src1_d,
+            src2_d,
+            dst_d,
+            ne0,
+            ne1,
+            nb01,
+            nb02,
+            nb11,
+            nb21,
+            item_ct1);
+      });
+}

data/ext/sources/ggml/src/ggml-sycl/add-id.hpp

@@ -0,0 +1,8 @@
+#ifndef GGML_SYCL_ADD_ID_HPP
+#define GGML_SYCL_ADD_ID_HPP
+
+#include "common.hpp"
+
+void ggml_sycl_add_id(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
+
+#endif // GGML_SYCL_ADD_ID_HPP

data/ext/sources/ggml/src/ggml-sycl/backend.hpp

@@ -18,22 +18,29 @@
 #include "concat.hpp"
 #include "conv.hpp"
 #include "convert.hpp"
+#include "count-equal.hpp"
 #include "cpy.hpp"
 #include "dequantize.hpp"
 #include "dmmv.hpp"
 #include "element_wise.hpp"
+#include "fattn.hpp"
 #include "gla.hpp"
 #include "im2col.hpp"
 #include "mmq.hpp"
 #include "mmvq.hpp"
 #include "norm.hpp"
 #include "outprod.hpp"
+#include "pad.hpp"
 #include "quantize.hpp"
 #include "quants.hpp"
+#include "roll.hpp"
 #include "rope.hpp"
 #include "set_rows.hpp"
+#include "ssm_conv.hpp"
 #include "softmax.hpp"
 #include "tsembd.hpp"
 #include "wkv.hpp"
+#include "pad_reflect_1d.hpp"
+
 
 #endif  // GGML_SYCL_BACKEND_HPP

data/ext/sources/ggml/src/ggml-sycl/binbcast.cpp

@@ -11,8 +11,8 @@ static void k_bin_bcast(const src0_t * src0, const src1_t * src1, dst_t * dst,
         int ne0, int ne1, int ne2, int ne3,
         int ne10, int ne11, int ne12, int ne13,
         /*int s0, */ int s1,  int s2,  int s3,
-        /*int s00,*/ int s01, int s02, int s03,
-        /*int s10,*/ int s11, int s12, int s13,
+        int s00, int s01, int s02, int s03,
+        int s10, int s11, int s12, int s13,
         const sycl::nd_item<3> &item_ct1) {
     const int i0s = item_ct1.get_local_range(2) * item_ct1.get_group(2) +
                     item_ct1.get_local_id(2);
@@ -44,7 +44,7 @@ static void k_bin_bcast(const src0_t * src0, const src1_t * src1, dst_t * dst,
     for (int i0 = i0s; i0 < ne0;
          i0 += item_ct1.get_local_range(2) * item_ct1.get_group_range(2)) {
         const int i10 = i0 % ne10;
-        dst_row[i0] = (dst_t)bin_op(src0 ? (float)src0_row[i0] : 0.0f, (float)src1_row[i10]);
+        dst_row[i0] = (dst_t)bin_op(src0 ? (float)src0_row[i0*s00] : 0.0f, (float)src1_row[i10*s10]);
     }
 }
 
@@ -53,8 +53,8 @@ static void k_bin_bcast_unravel(const src0_t * src0, const src1_t * src1, dst_t
         int ne0, int ne1, int ne2, int ne3,
         int ne10, int ne11, int ne12, int ne13,
         /*int s0, */ int s1,  int s2,  int s3,
-        /*int s00,*/ int s01, int s02, int s03,
-        /*int s10,*/ int s11, int s12, int s13,
+        int s00, int s01, int s02, int s03,
+        int s10, int s11, int s12, int s13,
         const sycl::nd_item<3> &item_ct1) {
 
     const int i = item_ct1.get_local_range(2) * item_ct1.get_group(2) +
@@ -82,7 +82,7 @@ static void k_bin_bcast_unravel(const src0_t * src0, const src1_t * src1, dst_t
     dst_t * dst_row = dst + i_dst;
 
     const int i10 = i0 % ne10;
-    dst_row[i0] = (dst_t)bin_op(src0 ? (float)src0_row[i0] : 0.0f, (float)src1_row[i10]);
+    dst_row[i0] = (dst_t)bin_op(src0 ? (float)src0_row[i0*s00] : 0.0f, (float)src1_row[i10*s10]);
 }
 
 
@@ -95,7 +95,8 @@ struct bin_bcast_sycl {
                     const int64_t ne3, const size_t nb00, const size_t nb01, const size_t nb02, const size_t nb03,
                     const size_t nb10, const size_t nb11, const size_t nb12, const size_t nb13, const size_t nb0,
                     const size_t nb1, const size_t nb2, const size_t nb3, const bool src0_is_contiguous,
-                    const bool src1_is_contiguous, const bool dst_is_contiguous, queue_ptr stream) {
+                    const bool src1_is_contiguous, const bool src0_is_permuted, const bool src1_is_permuted,
+                    queue_ptr stream) {
         int nr0 = ne10 / ne0;
         int nr1 = ne11/ne1;
         int nr2 = ne12/ne2;
@@ -123,7 +124,7 @@ struct bin_bcast_sycl {
             cnb[3] *= cne[3];
         };
 
-        if (src0_is_contiguous && src1_is_contiguous && dst_is_contiguous) {
+        if (src0_is_contiguous && src1_is_contiguous && !src0_is_permuted && !src1_is_permuted) {
             for (int i = 0; i < 4; i++) {
                 if (nr[i] != 1) {
                     break;
@@ -164,7 +165,7 @@ struct bin_bcast_sycl {
             size_t nb12 = cnb1[2];
             size_t nb13 = cnb1[3];
 
-            size_t s0 = nb0 / sizeof(dst_t);
+            // size_t s0 = nb0 / sizeof(dst_t);
             size_t s1 = nb1 / sizeof(dst_t);
             size_t s2 = nb2 / sizeof(dst_t);
             size_t s3 = nb3 / sizeof(dst_t);
@@ -196,9 +197,6 @@ struct bin_bcast_sycl {
             GGML_ASSERT(nb12 % sizeof(src1_t) == 0);
             GGML_ASSERT(nb13 % sizeof(src1_t) == 0);
 
-            GGML_ASSERT(s0 == 1);
-            GGML_ASSERT(s10 == 1);
-
             const int block_size = 128;
 
             int64_t hne0 = std::max(ne0/2LL, 1LL);
@@ -232,8 +230,8 @@ struct bin_bcast_sycl {
                         [=](sycl::nd_item<3> item_ct1) {
                             k_bin_bcast_unravel<bin_op>(
                                 src0_dd, src1_dd, dst_dd, ne0, ne1, ne2, ne3,
-                                ne10, ne11, ne12, ne13, s1, s2, s3, s01, s02,
-                                s03, s11, s12, s13, item_ct1);
+                                ne10, ne11, ne12, ne13, s1, s2, s3, s00, s01, s02,
+                                s03, s10, s11, s12, s13, item_ct1);
                         });
                 }
             } else {
@@ -251,7 +249,7 @@ struct bin_bcast_sycl {
                     [=](sycl::nd_item<3> item_ct1) {
                         k_bin_bcast<bin_op>(src0_dd, src1_dd, dst_dd, ne0, ne1,
                                             ne2, ne3, ne10, ne11, ne12, ne13,
-                                            s1, s2, s3, s01, s02, s03, s11, s12, s13,
+                                            s1, s2, s3, s00, s01, s02, s03, s10, s11, s12, s13,
                                             item_ct1);
                     });
             }
@@ -268,24 +266,27 @@ inline void ggml_sycl_op_bin_bcast(ggml_backend_sycl_context & ctx, const ggml_t
     if (src0->type == GGML_TYPE_F32 && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32) {
         op()((const float *) src0->data, (const float *) src1->data, (float *) dst->data, ne00, ne01, ne02, ne03, ne10,
              ne11, ne12, ne13, ne0, ne1, ne2, ne3, nb00, nb01, nb02, nb03, nb10, nb11, nb12, nb13, nb0, nb1, nb2, nb3,
-             ggml_is_contiguous(src0), ggml_is_contiguous(src1), ggml_is_contiguous(dst), main_stream);
+             ggml_is_contiguous(src0), ggml_is_contiguous(src1), ggml_is_permuted(src0), ggml_is_permuted(src1), main_stream);
     } else if (src0->type == GGML_TYPE_F16 && src1->type == GGML_TYPE_F16 && dst->type == GGML_TYPE_F16) {
         op()((const sycl::half *) src0->data, (const sycl::half *) src1->data, (sycl::half *) dst->data, ne00, ne01,
              ne02, ne03, ne10, ne11, ne12, ne13, ne0, ne1, ne2, ne3, nb00, nb01, nb02, nb03, nb10, nb11, nb12, nb13,
-             nb0, nb1, nb2, nb3, ggml_is_contiguous(src0), ggml_is_contiguous(src1), ggml_is_contiguous(dst),
+             nb0, nb1, nb2, nb3, ggml_is_contiguous(src0), ggml_is_contiguous(src1), ggml_is_permuted(src0), ggml_is_permuted(src1),
              main_stream);
     } else if (src0->type == GGML_TYPE_F16 && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F16) {
         op()((const sycl::half *) src0->data, (const float *) src1->data, (sycl::half *) dst->data, ne00, ne01, ne02,
              ne03, ne10, ne11, ne12, ne13, ne0, ne1, ne2, ne3, nb00, nb01, nb02, nb03, nb10, nb11, nb12, nb13, nb0, nb1,
-             nb2, nb3, ggml_is_contiguous(src0), ggml_is_contiguous(src1), ggml_is_contiguous(dst), main_stream);
+             nb2, nb3, ggml_is_contiguous(src0), ggml_is_contiguous(src1), ggml_is_permuted(src0), ggml_is_permuted(src1),
+             main_stream);
     } else if (src0->type == GGML_TYPE_I32 && src1->type == GGML_TYPE_I32 && dst->type == GGML_TYPE_I32) {
         op()((const int32_t *) src0->data, (const int32_t *) src1->data, (int32_t *) dst->data, ne00, ne01, ne02, ne03,
              ne10, ne11, ne12, ne13, ne0, ne1, ne2, ne3, nb00, nb01, nb02, nb03, nb10, nb11, nb12, nb13, nb0, nb1, nb2,
-             nb3, ggml_is_contiguous(src0), ggml_is_contiguous(src1), ggml_is_contiguous(dst), main_stream);
+             nb3, ggml_is_contiguous(src0), ggml_is_contiguous(src1), ggml_is_permuted(src0), ggml_is_permuted(src1),
+             main_stream);
     } else if (src0->type == GGML_TYPE_I16 && src1->type == GGML_TYPE_I16 && dst->type == GGML_TYPE_I16) {
         op()((const int16_t *) src0->data, (const int16_t *) src1->data, (int16_t *) dst->data, ne00, ne01, ne02, ne03,
              ne10, ne11, ne12, ne13, ne0, ne1, ne2, ne3, nb00, nb01, nb02, nb03, nb10, nb11, nb12, nb13, nb0, nb1, nb2,
-             nb3, ggml_is_contiguous(src0), ggml_is_contiguous(src1), ggml_is_contiguous(dst), main_stream);
+             nb3, ggml_is_contiguous(src0), ggml_is_contiguous(src1), ggml_is_permuted(src0), ggml_is_permuted(src1),
+             main_stream);
     } else {
         fprintf(stderr, "%s: unsupported types: dst: %s, src0: %s, src1: %s\n", __func__, ggml_type_name(dst->type),
                 ggml_type_name(src0->type), ggml_type_name(src1->type));
@@ -303,10 +304,6 @@ inline void ggml_sycl_op_sub(ggml_backend_sycl_context & ctx, ggml_tensor *dst)
     ggml_sycl_op_bin_bcast<bin_bcast_sycl<op_sub>>(ctx, dst->src[0], dst->src[1], dst);
 }
 
-inline void ggml_sycl_op_count_equal(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
-    ggml_sycl_op_bin_bcast<bin_bcast_sycl<op_count_equal>>(ctx, dst->src[0], dst->src[1], dst);
-}
-
 inline void ggml_sycl_op_mul(ggml_backend_sycl_context & ctx, ggml_tensor *dst) {
 
     ggml_sycl_op_bin_bcast<bin_bcast_sycl<op_mul>>(ctx, dst->src[0], dst->src[1], dst);
@@ -332,11 +329,6 @@ void ggml_sycl_sub(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
     ggml_sycl_op_sub(ctx, dst);
 }
 
-void ggml_sycl_count_equal(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
-    scope_op_debug_print scope_dbg_print(__func__, dst, /*num_src=*/2);
-    ggml_sycl_op_count_equal(ctx, dst);
-}
-
 void ggml_sycl_mul(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
     scope_op_debug_print scope_dbg_print(__func__, dst, /*num_src=*/2);
     ggml_sycl_op_mul(ctx, dst);

data/ext/sources/ggml/src/ggml-sycl/binbcast.hpp

@@ -16,12 +16,6 @@ static __dpct_inline__ float op_sub(const float a, const float b) {
     return a - b;
 }
 
-static __dpct_inline__ float op_count_equal(const float a, const float b) {
-    return (a == b) ? 1.0f : 0.0f;
-}
-
-void ggml_sycl_count_equal(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
-
 static __dpct_inline__ float op_mul(const float a, const float b) {
     return a * b;
 }