llama_cpp 0.15.3 → 0.15.4

data/vendor/tmp/llama.cpp/ggml-sycl.cpp

@@ -2944,6 +2944,57 @@ namespace dpct
     using shared_memory = detail::device_memory<T, shared, Dimension>;
 
 
+    template <typename T,
+            sycl::access::address_space addressSpace =
+                sycl::access::address_space::global_space,
+            sycl::memory_order memoryOrder = sycl::memory_order::relaxed,
+            sycl::memory_scope memoryScope = sycl::memory_scope::device>
+    inline T atomic_fetch_add(T *addr, T operand) {
+    auto atm =
+        sycl::atomic_ref<T, memoryOrder, memoryScope, addressSpace>(addr[0]);
+    return atm.fetch_add(operand);
+    }
+
+    template <sycl::access::address_space addressSpace =
+                sycl::access::address_space::global_space,
+            sycl::memory_order memoryOrder = sycl::memory_order::relaxed,
+            sycl::memory_scope memoryScope = sycl::memory_scope::device,
+            typename T1, typename T2>
+    inline T1 atomic_fetch_add(T1 *addr, T2 operand) {
+    auto atm =
+        sycl::atomic_ref<T1, memoryOrder, memoryScope, addressSpace>(addr[0]);
+    return atm.fetch_add(operand);
+    }
+
+    template <typename T, sycl::access::address_space addressSpace =
+                            sycl::access::address_space::global_space>
+    inline T atomic_fetch_add(T *addr, T operand,
+                            sycl::memory_order memoryOrder) {
+    switch (memoryOrder) {
+        case sycl::memory_order::relaxed:
+            return atomic_fetch_add<T, addressSpace, sycl::memory_order::relaxed,
+                                    sycl::memory_scope::device>(addr, operand);
+        case sycl::memory_order::acq_rel:
+            return atomic_fetch_add<T, addressSpace, sycl::memory_order::acq_rel,
+                                    sycl::memory_scope::device>(addr, operand);
+        case sycl::memory_order::seq_cst:
+            return atomic_fetch_add<T, addressSpace, sycl::memory_order::seq_cst,
+                                    sycl::memory_scope::device>(addr, operand);
+        default:
+            assert(false && "Invalid memory_order for atomics. Valid memory_order for "
+                            "atomics are: sycl::memory_order::relaxed, "
+                            "sycl::memory_order::acq_rel, sycl::memory_order::seq_cst!");
+        }
+    }
+
+    template <sycl::access::address_space addressSpace =
+                sycl::access::address_space::global_space,
+            typename T1, typename T2>
+    inline T1 atomic_fetch_add(T1 *addr, T2 operand,
+                            sycl::memory_order memoryOrder) {
+    atomic_fetch_add<T1, addressSpace>(addr, operand, memoryOrder);
+    }
+
 } // COPY from DPCT head files
 
 #define GGML_COMMON_DECL_SYCL
@@ -2971,20 +3022,19 @@ static int g_work_group_size = 0;
 // typedef sycl::half ggml_fp16_t;
 
 #define __SYCL_ARCH__ DPCT_COMPATIBILITY_TEMP
-#define VER_4VEC   610          //todo for hardward optimize.
+#define VER_4VEC   130          //todo for hardward optimize.
 #define VER_GEN9      700       //todo for hardward optimize.
 #define VER_GEN12 1000000       //todo for hardward optimize.
 #define VER_GEN13      (VER_GEN12 + 1030)   //todo for hardward optimize.
 
 #define GGML_SYCL_MAX_NODES 8192 //TODO: adapt to hardwares
 
-
-//define for XMX in Intel GPU
-//TODO: currently, it's not used for XMX really.
-#define SYCL_USE_XMX
+#if !defined(GGML_SYCL_FORCE_MMQ)
+    #define SYCL_USE_XMX
+#endif
 
 // max batch size to use MMQ kernels when tensor cores are available
-#define XMX_MAX_BATCH_SIZE 32
+#define MMQ_MAX_BATCH_SIZE 32
 
 
 #if defined(_MSC_VER)
@@ -3060,6 +3110,7 @@ void   ggml_sycl_get_device_description(int device, char * description, size_t d
 bool   ggml_backend_is_sycl(ggml_backend_t backend);
 int    ggml_backend_sycl_get_device(ggml_backend_t backend);
 int    get_main_device();
+static bool ggml_backend_buffer_is_sycl_split(ggml_backend_buffer_t buffer);
 void   print_ggml_tensor(const char*name, struct ggml_tensor *src);
 void   log_tensor_with_cnt(const char* name, struct ggml_tensor * src, int stop_cnt);
 
@@ -8830,12 +8881,11 @@ static void rope(
     dst[i + 1] = x0*sin_theta + x1*cos_theta;
 }
 
-template<typename T, bool has_pos>
+template<typename T, bool has_pos, bool has_freq_facs>
 static void rope_neox(
     const T * x, T * dst, int ncols, int n_dims, const int32_t * pos, float freq_scale, int p_delta_rows,
-    float ext_factor, float attn_factor, rope_corr_dims corr_dims, float theta_scale, float inv_ndims
-,
-    const sycl::nd_item<3> &item_ct1) {
+    float ext_factor, float attn_factor, rope_corr_dims corr_dims, float theta_scale, float inv_ndims,
+    const float * freq_factors, const sycl::nd_item<3> &item_ct1) {
     const int col = 2 * (item_ct1.get_local_range(1) * item_ct1.get_group(1) +
                          item_ct1.get_local_id(1));
 
@@ -8863,8 +8913,10 @@ static void rope_neox(
     float cur_rot = inv_ndims * ic - ib;
 
     const int p = has_pos ? pos[i2] : 0;
+    const float freq_factor = has_freq_facs ? freq_factors[ic/2] : 1.0f;
+
     const float theta_base =
-        p * freq_scale * dpct::pow(theta_scale, col / 2.0f);
+        p * freq_scale * dpct::pow(theta_scale, col / 2.0f)/freq_factor;
 
     float cos_theta, sin_theta;
     rope_yarn(theta_base, freq_scale, corr_dims, cur_rot, ext_factor, attn_factor, &cos_theta, &sin_theta);
@@ -12413,7 +12465,7 @@ static void rope_neox_sycl(const T *x, T *dst, int ncols, int n_dims, int nrows,
                            const int32_t *pos, float freq_scale,
                            int p_delta_rows, float freq_base, float ext_factor,
                            float attn_factor, rope_corr_dims corr_dims,
-                           dpct::queue_ptr stream) {
+                           const float * freq_factors, dpct::queue_ptr stream) {
     GGML_ASSERT(ncols % 2 == 0);
     const sycl::range<3> block_dims(1, SYCL_ROPE_BLOCK_SIZE, 1);
     const int num_blocks_x = (ncols + 2*SYCL_ROPE_BLOCK_SIZE - 1) / (2*SYCL_ROPE_BLOCK_SIZE);
@@ -12423,38 +12475,48 @@ static void rope_neox_sycl(const T *x, T *dst, int ncols, int n_dims, int nrows,
     const float inv_ndims = -1.0f / n_dims;
 
     if (pos == nullptr) {
-        /*
-        DPCT1049:42: The work-group size passed to the SYCL kernel may exceed
-        the limit. To get the device limit, query
-        info::device::max_work_group_size. Adjust the work-group size if needed.
-        */
         dpct::has_capability_or_fail(stream->get_device(),
                                      {sycl::aspect::fp16});
-
-        stream->parallel_for(
-            sycl::nd_range<3>(block_nums * block_dims, block_dims),
-            [=](sycl::nd_item<3> item_ct1) {
-                rope_neox<T, false>(x, dst, ncols, n_dims, pos, freq_scale,
-                                    p_delta_rows, ext_factor, attn_factor,
-                                    corr_dims, theta_scale, inv_ndims,
-                                    item_ct1);
-            });
+        if (freq_factors == nullptr) {
+            stream->parallel_for(
+                sycl::nd_range<3>(block_nums * block_dims, block_dims),
+                [=](sycl::nd_item<3> item_ct1) {
+                    rope_neox<T, false, false>(x, dst, ncols, n_dims, pos, freq_scale,
+                                        p_delta_rows, ext_factor, attn_factor,
+                                        corr_dims, theta_scale, inv_ndims, freq_factors,
+                                        item_ct1);
+                });
+        } else {
+            stream->parallel_for(
+                sycl::nd_range<3>(block_nums * block_dims, block_dims),
+                [=](sycl::nd_item<3> item_ct1) {
+                    rope_neox<T, false, true>(x, dst, ncols, n_dims, pos, freq_scale,
+                                        p_delta_rows, ext_factor, attn_factor,
+                                        corr_dims, theta_scale, inv_ndims, freq_factors,
+                                        item_ct1);
+                });
+        }
     } else {
-        /*
-        DPCT1049:43: The work-group size passed to the SYCL kernel may exceed
-        the limit. To get the device limit, query
-        info::device::max_work_group_size. Adjust the work-group size if needed.
-        */
         dpct::has_capability_or_fail(stream->get_device(),
                                      {sycl::aspect::fp16});
 
-        stream->parallel_for(
-            sycl::nd_range<3>(block_nums * block_dims, block_dims),
-            [=](sycl::nd_item<3> item_ct1) {
-                rope_neox<T, true>(x, dst, ncols, n_dims, pos, freq_scale,
-                                   p_delta_rows, ext_factor, attn_factor,
-                                   corr_dims, theta_scale, inv_ndims, item_ct1);
-            });
+        if (freq_factors == nullptr) {
+            stream->parallel_for(
+                sycl::nd_range<3>(block_nums * block_dims, block_dims),
+                [=](sycl::nd_item<3> item_ct1) {
+                    rope_neox<T, true, false>(x, dst, ncols, n_dims, pos, freq_scale,
+                                       p_delta_rows, ext_factor, attn_factor,
+                                       corr_dims, theta_scale, inv_ndims, freq_factors, item_ct1);
+                });
+        } else {
+            stream->parallel_for(
+                sycl::nd_range<3>(block_nums * block_dims, block_dims),
+                [=](sycl::nd_item<3> item_ct1) {
+                    rope_neox<T, true, true>(x, dst, ncols, n_dims, pos, freq_scale,
+                                       p_delta_rows, ext_factor, attn_factor,
+                                       corr_dims, theta_scale, inv_ndims, freq_factors, item_ct1);
+                });
+        }
     }
 }
 
@@ -13501,6 +13563,10 @@ inline void ggml_sycl_op_concat(const ggml_tensor *src0,
                                 const float *src0_dd, const float *src1_dd,
                                 float *dst_dd,
                                 const dpct::queue_ptr &main_stream) {
+#pragma message("TODO: generalize concat kernel for dim != 2")
+#pragma message("      https://github.com/ggerganov/llama.cpp/pull/7563")
+    int dim = dst->op_params[0];
+    GGML_ASSERT(dim == 2);
 
     GGML_ASSERT(src0->type == GGML_TYPE_F32);
     GGML_ASSERT(src1->type == GGML_TYPE_F32);
@@ -13986,9 +14052,7 @@ inline void ggml_sycl_op_rope(const ggml_tensor *src0, const ggml_tensor *src1,
                               ggml_tensor *dst, const float *src0_dd,
                               const float *src1_dd, float *dst_dd,
                               const dpct::queue_ptr &main_stream) {
-#pragma message("TODO: implement phi3 frequency factors support")
-#pragma message("      https://github.com/ggerganov/llama.cpp/pull/7225")
-    GGML_ASSERT(dst->src[2] == nullptr && "phi3 frequency factors not implemented yet");
+    const ggml_tensor * src2 = dst->src[2];
 
     GGML_ASSERT(src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16);
     GGML_ASSERT( dst->type == GGML_TYPE_F32 ||  dst->type == GGML_TYPE_F16);
@@ -14014,6 +14078,7 @@ inline void ggml_sycl_op_rope(const ggml_tensor *src0, const ggml_tensor *src1,
     memcpy(&beta_fast,   (int32_t *) dst->op_params +  9, sizeof(float));
     memcpy(&beta_slow,   (int32_t *) dst->op_params + 10, sizeof(float));
 
+    const float * freq_factors = nullptr;
     const int32_t * pos = nullptr;
     if ((mode & 1) == 0) {
         GGML_ASSERT(src1->type == GGML_TYPE_I32);
@@ -14024,6 +14089,16 @@ inline void ggml_sycl_op_rope(const ggml_tensor *src0, const ggml_tensor *src1,
     const bool is_neox = mode & 2;
     const bool is_glm  = mode & 4;
 
+    if (is_neox) {
+        pos = (const int32_t *) src1_dd;
+
+        if (src2 != nullptr) {
+            freq_factors = (const float *) src2->data;
+        }
+    } else {
+        GGML_ASSERT(src2 == nullptr && "TODO: freq_factors not implemented for !is_neox");
+    }
+
     rope_corr_dims corr_dims;
     ggml_rope_yarn_corr_dims(n_dims, n_orig_ctx, freq_base, beta_fast, beta_slow, corr_dims.v);
 
@@ -14035,13 +14110,13 @@ inline void ggml_sycl_op_rope(const ggml_tensor *src0, const ggml_tensor *src1,
         if (src0->type == GGML_TYPE_F32) {
             rope_neox_sycl(
                 (const float *)src0_dd, (float *)dst_dd, ne00, n_dims, nrows, pos, freq_scale, ne01, freq_base, ext_factor,
-                attn_factor, corr_dims, main_stream
+                attn_factor, corr_dims, freq_factors, main_stream
             );
         } else if (src0->type == GGML_TYPE_F16) {
             rope_neox_sycl((const sycl::half *)src0_dd, (sycl::half *)dst_dd,
                            ne00, n_dims, nrows, pos, freq_scale, ne01,
                            freq_base, ext_factor, attn_factor, corr_dims,
-                           main_stream);
+                           freq_factors, main_stream);
         } else {
             GGML_ASSERT(false);
         }
@@ -15108,7 +15183,7 @@ static void ggml_sycl_mul_mat_batched_sycl(const ggml_tensor *src0,
     const int64_t r2 = ne12/ne02;
     const int64_t r3 = ne13/ne03;
 
-    if (r2 == 1 && r3 == 1 && src0->nb[2]*src0->ne[2] == src0->nb[3] && src1->nb[2]*src1->ne[2] == src1->nb[3]) {
+    if (r2 == 1 && r3 == 1 && ggml_is_contiguous_2(src0) && ggml_is_contiguous_2(src1)) {
         // there is no broadcast and src0, src1 are contiguous across dims 2, 3
         SYCL_CHECK(CHECK_TRY_ERROR(dpct::gemm_batch(
             *g_sycl_handles[g_main_device], oneapi::mkl::transpose::trans,
@@ -15173,6 +15248,29 @@ catch (sycl::exception const &exc) {
   std::exit(1);
 }
 
+inline bool ggml_sycl_supports_mmq(enum ggml_type type) {
+    // TODO: accuracy issues in MMQ
+    return false;
+}
+
+bool ggml_sycl_supports_dmmv(enum ggml_type type) {
+    switch (type) {
+        case GGML_TYPE_Q4_0:
+        case GGML_TYPE_Q4_1:
+        case GGML_TYPE_Q5_0:
+        case GGML_TYPE_Q5_1:
+        case GGML_TYPE_Q8_0:
+        case GGML_TYPE_Q2_K:
+        case GGML_TYPE_Q3_K:
+        case GGML_TYPE_Q4_K:
+        case GGML_TYPE_Q5_K:
+        case GGML_TYPE_Q6_K:
+        case GGML_TYPE_F16:
+            return true;
+        default:
+            return false;
+    }
+}
 
 static void ggml_sycl_mul_mat(const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
     const bool all_on_device =
@@ -15189,75 +15287,42 @@ static void ggml_sycl_mul_mat(const ggml_tensor * src0, const ggml_tensor * src1
         }
     }
 
-#ifdef SYCL_USE_XMX
-    const bool use_xmx = true;
-#else
-    const bool use_xmx = false;
-#endif
+    // check data types and tensor shapes for custom matrix multiplication kernels:
+    bool use_dequantize_mul_mat_vec = ggml_sycl_supports_dmmv(src0->type)
+        && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
+        && src0->ne[0] % GGML_SYCL_DMMV_X == 0 && src1->ne[1] == 1;
+
+    bool use_mul_mat_vec_q =  ggml_is_quantized(src0->type)
+        && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
+        && src1->ne[1] <= MMVQ_MAX_BATCH_SIZE;
 
-    // debug helpers
-    //printf("src0: %8d %8d %8d %8d\n", src0->ne[0], src0->ne[1], src0->ne[2], src0->ne[3]);
-    //printf("      %8d %8d %8d %8d\n", src0->nb[0], src0->nb[1], src0->nb[2], src0->nb[3]);
-    //printf("src1: %8d %8d %8d %8d\n", src1->ne[0], src1->ne[1], src1->ne[2], src1->ne[3]);
-    //printf("      %8d %8d %8d %8d\n", src1->nb[0], src1->nb[1], src1->nb[2], src1->nb[3]);
-    //printf("src0 is contiguous %d, transposed %d, type = %s, name = %s\n", ggml_is_contiguous(src0), ggml_is_transposed(src0), ggml_type_name(src0->type), src0->name);
-    //printf("src1 is contiguous %d, transposed %d, type = %s, name = %s\n", ggml_is_contiguous(src1), ggml_is_transposed(src1), ggml_type_name(src1->type), src1->name);
+    bool use_mul_mat_q =  ggml_sycl_supports_mmq(src0->type)
+        && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32;
+
+    // mmvq and mmq need the __dp4a instruction which is available for gen12+
+    // Workaround in https://github.com/ggerganov/llama.cpp/commit/95f84d5ce8b449a9b16009434aca800df504a02e
+    use_mul_mat_q = use_mul_mat_q && (src0->type != GGML_TYPE_IQ2_XXS);
+#ifdef SYCL_USE_XMX
+    use_mul_mat_q = use_mul_mat_q && (src1->ne[1] <= MMQ_MAX_BATCH_SIZE);
+#endif // SYCL_USE_XMX
 
-    if (!split && all_on_device && !use_xmx && src0->type == GGML_TYPE_F16 && ggml_is_permuted(src0) && ggml_is_permuted(src1) && src1->ne[1] == 1) {
+    if (!split && src0->type == GGML_TYPE_F16 && ggml_is_permuted(src0) && ggml_is_permuted(src1) && src1->ne[1] == 1) {
         // KQ single-batch
-        // GGML_SYCL_DEBUG("ggml_sycl_mul_mat_vec_p021\n");
         ggml_sycl_mul_mat_vec_p021(src0, src1, dst);
-    } else if (!split && all_on_device && !use_xmx && src0->type == GGML_TYPE_F16 && !ggml_is_contiguous(src0) && !ggml_is_transposed(src1) && src1->ne[1] == 1) {
+    } else if (!split && src0->type == GGML_TYPE_F16 && !ggml_is_contiguous(src0) && !ggml_is_transposed(src1) && src1->ne[1] == 1) {
         // KQV single-batch
-        // GGML_SYCL_DEBUG("ggml_sycl_mul_mat_vec_nc\n");
         ggml_sycl_mul_mat_vec_nc(src0, src1, dst);
-    } else if (!split && all_on_device && use_xmx && src0->type == GGML_TYPE_F16 && !ggml_is_transposed(src0) && !ggml_is_transposed(src1)) {
+    } else if (!split && src0->type == GGML_TYPE_F16 && (src1->type == GGML_TYPE_F16) && !ggml_is_transposed(src0) && !ggml_is_transposed(src1) && src1->ne[2]*src1->ne[3] > 1) {
         // KQ + KQV multi-batch
-        // GGML_SYCL_DEBUG("ggml_sycl_mul_mat_batched_sycl\n");
         ggml_sycl_mul_mat_batched_sycl(src0, src1, dst);
-    } else if (src0->type == GGML_TYPE_F32) {
-        // GGML_SYCL_DEBUG("ggml_sycl_op_mul_mat\n");
-        ggml_sycl_op_mul_mat(src0, src1, dst, ggml_sycl_op_mul_mat_sycl, false);
-    } else if (ggml_is_quantized(src0->type) || src0->type == GGML_TYPE_F16) {
-        // GGML_SYCL_DEBUG("ggml_is_quantized or GGML_TYPE_F16\n");
-        if (src1->ne[1] == 1 && src0->ne[0] % GGML_SYCL_DMMV_X == 0) {
-#ifdef GGML_SYCL_FORCE_DMMV
-            const bool use_mul_mat_vec_q = false;
-#else
-            bool use_mul_mat_vec_q = min_compute_capability >= VER_4VEC && ggml_is_quantized(src0->type);
-            use_mul_mat_vec_q = use_mul_mat_vec_q ||
-                (src0->type == GGML_TYPE_IQ2_XXS) || (src0->type == GGML_TYPE_IQ2_XS) || (src0->type == GGML_TYPE_IQ2_S) ||
-                (src0->type == GGML_TYPE_IQ3_XXS) || (src0->type == GGML_TYPE_IQ3_S) ||
-                (src0->type == GGML_TYPE_IQ4_NL) || (src0->type == GGML_TYPE_IQ4_XS) ||
-                (src0->type == GGML_TYPE_IQ1_S) || (src0->type == GGML_TYPE_IQ1_M);
-
-
-#endif // GGML_SYCL_FORCE_DMMV
-
-            if (use_mul_mat_vec_q) {
-                // GGML_SYCL_DEBUG("ggml_sycl_mul_mat ggml_sycl_op_mul_mat_vec_q path\n");
-                ggml_sycl_op_mul_mat(src0, src1, dst, ggml_sycl_op_mul_mat_vec_q, true);
-            } else {
-                // GGML_SYCL_DEBUG("ggml_sycl_mul_mat ggml_sycl_op_dequantize_mul_mat_vec path\n");
-                ggml_sycl_op_mul_mat(src0, src1, dst, ggml_sycl_op_dequantize_mul_mat_vec, false);
-            }
-        } else {
-            bool use_mul_mat_q = min_compute_capability >= VER_4VEC && ggml_is_quantized(src0->type);
-
-            if (use_xmx && min_compute_capability >= VER_GEN9 && src1->ne[1] > XMX_MAX_BATCH_SIZE) {
-                use_mul_mat_q = false;
-            }
-
-            if (use_mul_mat_q) {
-                // GGML_SYCL_DEBUG("ggml_sycl_mul_mat ggml_sycl_op_mul_mat_q path\n");
-                ggml_sycl_op_mul_mat(src0, src1, dst, ggml_sycl_op_mul_mat_q, true);
-            } else {
-                // GGML_SYCL_DEBUG("ggml_sycl_mul_mat ggml_sycl_op_mul_mat_sycl path\n");
-                ggml_sycl_op_mul_mat(src0, src1, dst, ggml_sycl_op_mul_mat_sycl, false);
-            }
-        }
+    } else if (use_dequantize_mul_mat_vec) {
+        ggml_sycl_op_mul_mat(src0, src1, dst, ggml_sycl_op_dequantize_mul_mat_vec, false);
+    } else if (use_mul_mat_vec_q) {
+        ggml_sycl_op_mul_mat(src0, src1, dst, ggml_sycl_op_mul_mat_vec_q, true);
+    } else if (use_mul_mat_q) {
+        ggml_sycl_op_mul_mat(src0, src1, dst, ggml_sycl_op_mul_mat_q, true);
     } else {
-        GGML_ASSERT(false);
+        ggml_sycl_op_mul_mat(src0, src1, dst, ggml_sycl_op_mul_mat_sycl, false);
     }
 }
 
@@ -15434,22 +15499,86 @@ static void ggml_sycl_mul_mat_id_sycl(ggml_tensor * dst) {
 }
 #endif
 
+struct mmid_row_mapping {
+    int32_t i1;
+    int32_t i2;
+};
+
+__dpct_inline__ static void k_copy_src1_to_contiguous(
+    const char *__restrict__ src1_original, char *__restrict__ src1_contiguous,
+    int *__restrict__ cur_src1_row, mmid_row_mapping *__restrict__ row_mapping,
+    const char *__restrict ids, int64_t i02, size_t ids_nb1, size_t ids_nb0,
+    int64_t ne11, int64_t ne10, size_t nb11, size_t nb12,
+    const sycl::nd_item<3> &item_ct1, int &src1_row) {
+    int32_t iid1 = item_ct1.get_group(2);
+    int32_t id = item_ct1.get_group(1);
+
+    const int32_t row_id_i = *(const int32_t *) (ids + iid1*ids_nb1 + id*ids_nb0);
+
+    if (row_id_i != i02) {
+        return;
+    }
+
+    const int64_t i11 = id % ne11;
+    const int64_t i12 = iid1;
+
+    if (item_ct1.get_local_id(2) == 0) {
+        src1_row =
+            dpct::atomic_fetch_add<sycl::access::address_space::generic_space>(
+                cur_src1_row, 1);
+        row_mapping[src1_row] = {id, iid1};
+    }
+    /*
+    DPCT1065:194: Consider replacing sycl::nd_item::barrier() with
+    sycl::nd_item::barrier(sycl::access::fence_space::local_space) for better
+    performance if there is no access to global memory.
+    */
+    item_ct1.barrier();
+
+    const float * src1_row_original = (const float *)(src1_original + i11*nb11 + i12*nb12);
+    float * src1_row_contiguous = (float *)(src1_contiguous + src1_row*nb11);
+
+#pragma unroll
+    for (int i = item_ct1.get_local_id(2); i < ne10;
+         i += item_ct1.get_local_range(2)) {
+        src1_row_contiguous[i] = src1_row_original[i];
+    }
+}
+
+__dpct_inline__ static void k_copy_dst_from_contiguous(
+    char *__restrict__ dst_original, const char *__restrict__ dst_contiguous,
+    const mmid_row_mapping *__restrict__ row_mapping, int64_t ne0, size_t nb1,
+    size_t nb2, const sycl::nd_item<3> &item_ct1) {
+    int32_t i = item_ct1.get_group(2);
+
+    const int32_t i1 = row_mapping[i].i1;
+    const int32_t i2 = row_mapping[i].i2;
+
+    const float * dst_row_contiguous = (const float *)(dst_contiguous + i*nb1);
+    float * dst_row_original = (float *)(dst_original + i1*nb1 + i2*nb2);
+
+#pragma unroll
+    for (int j = item_ct1.get_local_id(2); j < ne0;
+         j += item_ct1.get_local_range(2)) {
+        dst_row_original[j] = dst_row_contiguous[j];
+    }
+}
+
 static void ggml_sycl_mul_mat_id(const ggml_tensor *src0,
                                  const ggml_tensor *src1,
                                  ggml_tensor *dst) try {
-    GGML_ASSERT(src0->backend != GGML_BACKEND_TYPE_GPU_SPLIT &&
-                "mul_mat_id does not support split buffers");
+    GGML_ASSERT(!ggml_backend_buffer_is_sycl_split(src0->buffer) && "mul_mat_id does not support split buffers");
+
     const ggml_tensor *ids = dst->src[2];
-    const dpct::queue_ptr stream = g_syclStreams[g_main_device][0];
+    GGML_TENSOR_BINARY_OP_LOCALS
 
-    const size_t nb11 = src1->nb[1];
-    const size_t nb1 = dst->nb[1];
+    const dpct::queue_ptr stream = g_syclStreams[g_main_device][0];
 
-    const int32_t id = ((int32_t *)dst->op_params)[0];
-    const int32_t n_as = src0->ne[2];
+    const int64_t n_as = ne02;
+    const int64_t n_ids = ids->ne[0];
 
     std::vector<char> ids_host(ggml_nbytes(ids));
-    const char *ids_dev = (const char *)ids->data;
+    const char * ids_dev = (const char *) ids->data;
 
     SYCL_CHECK(CHECK_TRY_ERROR(
         stream->memcpy(ids_host.data(), ids_dev, ggml_nbytes(ids))));
@@ -15489,24 +15618,40 @@ static void ggml_sycl_mul_mat_id(const ggml_tensor *src0,
 
     src0_row.ne[2] = 1;
     src0_row.ne[3] = 1;
-    src0_row.nb[3] = src0->nb[2];
-
-    if (src1->ne[1] == 1) {
-        for (int64_t i01 = 0; i01 < ids->ne[1]; i01++) {
-            const int32_t row_id =
-                *(const int32_t *)(ids_host.data() + i01 * ids->nb[1] +
-                                   id * ids->nb[0]);
-
-            GGML_ASSERT(row_id >= 0 && row_id < n_as);
+    src0_row.nb[3] = nb02;
+
+    src1_row.ne[1] = 1;
+    src1_row.ne[2] = 1;
+    src1_row.ne[3] = 1;
+    src1_row.nb[2] = nb11;
+    src1_row.nb[3] = nb11;
+
+    dst_row.ne[1] = 1;
+    dst_row.ne[2] = 1;
+    dst_row.ne[3] = 1;
+    dst_row.nb[2] = nb1;
+    dst_row.nb[3] = nb1;
+    if (ne12 == 1) {
+        for (int64_t iid1 = 0; iid1 < ids->ne[1]; iid1++) {
+            for (int64_t id = 0; id < n_ids; id++) {
+                const int32_t i02 = *(const int32_t *) (ids_host.data() + iid1*ids->nb[1] + id*ids->nb[0]);
+                GGML_ASSERT(i02 >= 0 && i02 < n_as);
+
+                const int64_t i11 = id % ne11;
+                const int64_t i12 = iid1;
+
+                const int64_t i1 = id;
+                const int64_t i2 = i12;
 
             src0_row_extra.data_device[g_main_device] =
-                src0_original + row_id * src0->nb[2];
+                src0_original + i02*nb02;
             src1_row_extra.data_device[g_main_device] =
-                src1_original + i01 * src1->nb[1];
+                src1_original + + i11*nb11 + i12*nb12;
             dst_row_extra.data_device[g_main_device] =
-                dst_original + i01 * dst->nb[1];
+                dst_original + i1*nb1   + i2*nb2;
 
             ggml_sycl_mul_mat(&src0_row, &src1_row, &dst_row);
+            }
         }
     } else {
         sycl_pool_alloc<char> src1_contiguous(sizeof(float)*ggml_nelements(src1));
@@ -15515,64 +15660,98 @@ static void ggml_sycl_mul_mat_id(const ggml_tensor *src0,
         src1_row_extra.data_device[g_main_device] = src1_contiguous.get();
         dst_row_extra.data_device[g_main_device]  =  dst_contiguous.get();
 
-        for (int32_t row_id = 0; row_id < n_as; ++row_id) {
+        for (int64_t i02 = 0; i02 < n_as; i02++) {
             int64_t num_src1_rows = 0;
-            for (int64_t i01 = 0; i01 < ids->ne[1]; i01++) {
-                const int32_t row_id_i = *(const int32_t *) (ids_host.data() + i01*ids->nb[1] + id*ids->nb[0]);
+            for (int64_t iid1 = 0; iid1 < ids->ne[1]; iid1++) {
+                for (int64_t id = 0; id < n_ids; id++) {
+                    const int32_t row_id_i = *(const int32_t *) (ids_host.data() + iid1*ids->nb[1] + id*ids->nb[0]);
 
-                if (row_id_i != row_id) {
-                    continue;
-                }
+                    GGML_ASSERT(row_id_i >= 0 && row_id_i < n_as);
 
-                GGML_ASSERT(row_id >= 0 && row_id < n_as);
+                    if (row_id_i != i02) {
+                        continue;
+                    }
 
-                SYCL_CHECK(CHECK_TRY_ERROR(
-                    stream->memcpy(src1_contiguous.get() + num_src1_rows * nb11,
-                                   src1_original + i01 * nb11, nb11)));
-                num_src1_rows++;
+                    num_src1_rows++;
+                }
             }
 
             if (num_src1_rows == 0) {
                 continue;
             }
 
-            src0_row_extra.data_device[g_main_device] =
-                src0_original + row_id * src0->nb[2];
 
+            sycl_pool_alloc<int> dev_cur_src1_row(1);
+            sycl_pool_alloc<mmid_row_mapping> dev_row_mapping(num_src1_rows);
+            SYCL_CHECK(CHECK_TRY_ERROR(
+                stream->memset(dev_cur_src1_row.get(), 0, sizeof(int))));
+
+            {
+                sycl::range<3> block_dims(1, 1, std::min((unsigned int)ne10, 768u));
+                sycl::range<3> grid_dims(1, n_ids, ids->ne[1]);
+                stream->submit([&](sycl::handler &cgh) {
+                    sycl::local_accessor<int, 0> src1_row_acc(cgh);
+
+                    char *__restrict src1_contiguous_get =
+                        src1_contiguous.get();
+                    int *__restrict dev_cur_src1_row_get =
+                        dev_cur_src1_row.get();
+                    mmid_row_mapping *__restrict dev_row_mapping_get =
+                        dev_row_mapping.get();
+                    size_t ids_nb_ct6 = ids->nb[1];
+                    size_t ids_nb_ct7 = ids->nb[0];
+
+                    cgh.parallel_for(
+                        sycl::nd_range<3>(grid_dims * block_dims, block_dims),
+                        [=](sycl::nd_item<3> item_ct1) {
+                            k_copy_src1_to_contiguous(
+                                src1_original, src1_contiguous_get,
+                                dev_cur_src1_row_get,
+                                dev_row_mapping_get, ids_dev, i02,
+                                ids_nb_ct6, ids_nb_ct7, ne11, ne10, nb11, nb12,
+                                item_ct1, src1_row_acc);
+                        });
+                });
+            }
+
+            src0_row_extra.data_device[g_main_device] = src0_original + i02*nb02;
+
+            GGML_ASSERT(nb11 == sizeof(float)*ne10);
+            GGML_ASSERT(nb1 == sizeof(float)*ne0);
             src1_row.ne[1] = num_src1_rows;
-            dst_row.ne[1] = num_src1_rows;
 
             src1_row.nb[1] = nb11;
             src1_row.nb[2] = num_src1_rows*nb11;
             src1_row.nb[3] = num_src1_rows*nb11;
 
+            dst_row.ne[1] = num_src1_rows;
             dst_row.nb[1] = nb1;
             dst_row.nb[2] = num_src1_rows*nb1;
             dst_row.nb[3] = num_src1_rows*nb1;
 
             ggml_sycl_mul_mat(&src0_row, &src1_row, &dst_row);
 
-            num_src1_rows = 0;
-            for (int64_t i01 = 0; i01 < ids->ne[1]; i01++) {
-                const int32_t row_id_i = *(const int32_t *) (ids_host.data() + i01*ids->nb[1] + id*ids->nb[0]);
-
-                if (row_id_i != row_id) {
-                    continue;
-                }
-
-                GGML_ASSERT(row_id >= 0 && row_id < n_as);
-
-                SYCL_CHECK(CHECK_TRY_ERROR(stream->memcpy(
-                    dst_original + i01 * nb1,
-                    dst_contiguous.get() + num_src1_rows * nb1, nb1)));
-                num_src1_rows++;
+            {
+                sycl::range<3> block_dims(1, 1, std::min((unsigned int)ne0, 768u));
+                sycl::range<3> grid_dims(1, 1, num_src1_rows);
+                stream->submit([&](sycl::handler &cgh) {
+                    const char *__restrict dst_contiguous_get =
+                        dst_contiguous.get();
+                    const mmid_row_mapping *__restrict dev_row_mapping_get =
+                        dev_row_mapping.get();
+
+                    cgh.parallel_for(
+                        sycl::nd_range<3>(grid_dims * block_dims, block_dims),
+                        [=](sycl::nd_item<3> item_ct1) {
+                            k_copy_dst_from_contiguous(dst_original,
+                                                       dst_contiguous_get,
+                                                       dev_row_mapping_get,
+                                                       ne0, nb1, nb2, item_ct1);
+                        });
+                });
             }
         }
     }
-
-    if (dst->backend == GGML_BACKEND_TYPE_CPU) {
-        SYCL_CHECK(CHECK_TRY_ERROR(stream->wait()));
-    }
 }
 catch (sycl::exception const &exc) {
   std::cerr << exc.what() << "Exception caught at file:" << __FILE__
@@ -16555,10 +16734,9 @@ GGML_CALL static const char * ggml_backend_sycl_split_buffer_get_name(ggml_backe
     UNUSED(buffer);
 }
 
-// unused at the moment
-//static bool ggml_backend_buffer_is_sycl_split(ggml_backend_buffer_t buffer) {
-//    return buffer->iface.get_name == ggml_backend_sycl_split_buffer_get_name;
-//}
+static bool ggml_backend_buffer_is_sycl_split(ggml_backend_buffer_t buffer) {
+   return buffer->iface.get_name == ggml_backend_sycl_split_buffer_get_name;
+}
 
 GGML_CALL static void ggml_backend_sycl_split_buffer_free_buffer(ggml_backend_buffer_t buffer) {
     ggml_backend_sycl_split_buffer_context * ctx = (ggml_backend_sycl_split_buffer_context *)buffer->context;