ci : fix save-load test invokations

ggml/src/ggml-cpu/ggml-cpu-quants.c

@@ -11718,12 +11718,9 @@ void ggml_vec_dot_iq1_m_q8_K  (int n, float * GGML_RESTRICT s, size_t bs, const
 
 #elif defined __AVX2__
 
-    const __m256i mask = _mm256_set1_epi16(0x7);
+    const __m256i mask = _mm256_set1_epi16(2 * 0x7);
     const __m256i mone = _mm256_set1_epi16(1);
     const __m256i mone8 = _mm256_set1_epi8(1);
-    const __m256i mtwo8 = _mm256_set1_epi8(2);
-    // VPSHUFB cannot cross 128-bit lanes so odd shifts go to upper half.
-    const __m256i scales_shift = _mm256_set_epi64x(9, 3, 6, 0);
 
     __m256 accum1 = _mm256_setzero_ps();
     __m256 accum2 = _mm256_setzero_ps();
@@ -11735,14 +11732,6 @@ void ggml_vec_dot_iq1_m_q8_K  (int n, float * GGML_RESTRICT s, size_t bs, const
         const uint16_t * sc = (const uint16_t *)x[i].scales;
 
         scale.u16 = (sc[0] >> 12) | ((sc[1] >> 8) & 0x00f0) | ((sc[2] >> 4) & 0x0f00) | (sc[3] & 0xf000);
-        // Extract 3-bit scales (16 values)
-        __m256i scales = _mm256_set1_epi64x(*(const uint64_t*)sc);
-        scales = _mm256_srlv_epi64(scales, scales_shift);
-        scales = _mm256_add_epi16(_mm256_slli_epi16(_mm256_and_si256(scales, mask), 1), mone);
-
-        // Indices to repeat each scale 8 times.
-        __m256i scales_idx1 = _mm256_set1_epi16(0x0100);
-        __m256i scales_idx2 = _mm256_add_epi8(scales_idx1, _mm256_set1_epi8(8));
 
         __m256i sumi1 = _mm256_setzero_si256();
         __m256i sumi2 = _mm256_setzero_si256();
@@ -11788,12 +11777,11 @@ void ggml_vec_dot_iq1_m_q8_K  (int n, float * GGML_RESTRICT s, size_t bs, const
             const __m256i dot3 = _mm256_maddubs_epi16(mone8, _mm256_sign_epi8(q8b_1, delta1));
             const __m256i dot4 = _mm256_maddubs_epi16(mone8, _mm256_sign_epi8(q8b_2, delta2));
 
-            __m256i scale1 = _mm256_shuffle_epi8(scales, scales_idx1);
-            __m256i scale2 = _mm256_shuffle_epi8(scales, scales_idx2);
-
-            scales_idx1 = _mm256_add_epi8(scales_idx1, mtwo8);
-            scales_idx2 = _mm256_add_epi8(scales_idx2, mtwo8);
+            __m256i scale1 = MM256_SET_M128I(_mm_set1_epi16(sc[ib/2] >> 2), _mm_set1_epi16(sc[ib/2] << 1));
+            __m256i scale2 = MM256_SET_M128I(_mm_set1_epi16(sc[ib/2] >> 8), _mm_set1_epi16(sc[ib/2] >> 5));
 
+            scale1 = _mm256_add_epi16(_mm256_and_si256(scale1, mask), mone);
+            scale2 = _mm256_add_epi16(_mm256_and_si256(scale2, mask), mone);
             const __m256i p1 = _mm256_madd_epi16(dot1, scale1);
             const __m256i p2 = _mm256_madd_epi16(dot2, scale2);
             const __m256i p3 = _mm256_madd_epi16(dot3, scale1);

ggml/src/ggml-cpu/ggml-cpu.c

@@ -6648,135 +6648,6 @@ static void ggml_compute_forward_repeat_back(
 
 // ggml_compute_forward_concat
 
-static void ggml_compute_forward_concat_any(
-    const struct ggml_compute_params * params,
-    struct ggml_tensor * dst) {
-
-    const struct ggml_tensor * src0 = dst->src[0];
-    const struct ggml_tensor * src1 = dst->src[1];
-
-    const size_t len = ggml_type_size(src0->type);
-
-    const int ith = params->ith;
-    const int nth = params->nth;
-
-    GGML_TENSOR_BINARY_OP_LOCALS
-
-    const int32_t dim = ggml_get_op_params_i32(dst, 0);
-
-    GGML_ASSERT(dim >= 0 && dim < 4);
-
-    int64_t o[4] = {0, 0, 0, 0};
-    o[dim] = src0->ne[dim];
-
-    const char * x;
-
-    // TODO: smarter multi-theading
-    for (int i3 = 0; i3 < ne3; i3++) {
-        for (int i2 = ith; i2 < ne2; i2 += nth) {
-            for (int i1 = 0; i1 < ne1; i1++) {
-                for (int i0 = 0; i0 < ne0; i0++) {
-                    if (i0 < ne00 && i1 < ne01 && i2 < ne02 && i3 < ne03) {
-                        x = (const char *)src0->data + (i0       )*nb00 + (i1       )*nb01 + (i2       )*nb02 + (i3       )*nb03;
-                    } else {
-                        x = (const char *)src1->data + (i0 - o[0])*nb10 + (i1 - o[1])*nb11 + (i2 - o[2])*nb12 + (i3 - o[3])*nb13;
-                    }
-
-                    char * y = (char *)dst->data + i0*nb0 + i1*nb1 + i2*nb2 + i3*nb3;
-
-                    memcpy(y, x, len);
-                }
-            }
-        }
-    }
-}
-
-static void ggml_compute_forward_concat_i8(
-    const struct ggml_compute_params * params,
-    struct ggml_tensor * dst) {
-
-    const struct ggml_tensor * src0 = dst->src[0];
-    const struct ggml_tensor * src1 = dst->src[1];
-
-    GGML_ASSERT(ggml_type_size(src0->type) == sizeof(int8_t));
-
-    const int ith = params->ith;
-    const int nth = params->nth;
-
-    GGML_TENSOR_BINARY_OP_LOCALS
-
-    const int32_t dim = ggml_get_op_params_i32(dst, 0);
-
-    GGML_ASSERT(dim >= 0 && dim < 4);
-
-    int64_t o[4] = {0, 0, 0, 0};
-    o[dim] = src0->ne[dim];
-
-    const int8_t * x;
-
-    // TODO: smarter multi-theading
-    for (int i3 = 0; i3 < ne3; i3++) {
-        for (int i2 = ith; i2 < ne2; i2 += nth) {
-            for (int i1 = 0; i1 < ne1; i1++) {
-                for (int i0 = 0; i0 < ne0; i0++) {
-                    if (i0 < ne00 && i1 < ne01 && i2 < ne02 && i3 < ne03) {
-                        x = (const int8_t *) ((const char *)src0->data + (i0       )*nb00 + (i1       )*nb01 + (i2       )*nb02 + (i3       )*nb03);
-                    } else {
-                        x = (const int8_t *) ((const char *)src1->data + (i0 - o[0])*nb10 + (i1 - o[1])*nb11 + (i2 - o[2])*nb12 + (i3 - o[3])*nb13);
-                    }
-
-                    int8_t * y = (int8_t *)((char *)dst->data + i0*nb0 + i1*nb1 + i2*nb2 + i3*nb3);
-
-                    *y = *x;
-                }
-            }
-        }
-    }
-}
-
-static void ggml_compute_forward_concat_f16(
-    const struct ggml_compute_params * params,
-    struct ggml_tensor * dst) {
-
-    const struct ggml_tensor * src0 = dst->src[0];
-    const struct ggml_tensor * src1 = dst->src[1];
-
-    GGML_ASSERT(ggml_type_size(src0->type) == sizeof(ggml_fp16_t));
-
-    const int ith = params->ith;
-    const int nth = params->nth;
-
-    GGML_TENSOR_BINARY_OP_LOCALS
-
-    const int32_t dim = ggml_get_op_params_i32(dst, 0);
-
-    GGML_ASSERT(dim >= 0 && dim < 4);
-
-    int64_t o[4] = {0, 0, 0, 0};
-    o[dim] = src0->ne[dim];
-
-    const ggml_fp16_t * x;
-
-    // TODO: smarter multi-theading
-    for (int i3 = 0; i3 < ne3; i3++) {
-        for (int i2 = ith; i2 < ne2; i2 += nth) {
-            for (int i1 = 0; i1 < ne1; i1++) {
-                for (int i0 = 0; i0 < ne0; i0++) {
-                    if (i0 < ne00 && i1 < ne01 && i2 < ne02 && i3 < ne03) {
-                        x = (const ggml_fp16_t *) ((const char *)src0->data + (i0       )*nb00 + (i1       )*nb01 + (i2       )*nb02 + (i3       )*nb03);
-                    } else {
-                        x = (const ggml_fp16_t *) ((const char *)src1->data + (i0 - o[0])*nb10 + (i1 - o[1])*nb11 + (i2 - o[2])*nb12 + (i3 - o[3])*nb13);
-                    }
-
-                    ggml_fp16_t * y = (ggml_fp16_t *)((char *)dst->data + i0*nb0 + i1*nb1 + i2*nb2 + i3*nb3);
-
-                    *y = *x;
-                }
-            }
-        }
-    }
-}
-
 static void ggml_compute_forward_concat_f32(
     const struct ggml_compute_params * params,
     struct ggml_tensor * dst) {
@@ -6784,7 +6655,7 @@ static void ggml_compute_forward_concat_f32(
     const struct ggml_tensor * src0 = dst->src[0];
     const struct ggml_tensor * src1 = dst->src[1];
 
-    GGML_ASSERT(ggml_type_size(src0->type) == sizeof(float));
+    GGML_ASSERT(src0->nb[0] == sizeof(float));
 
     const int ith = params->ith;
     const int nth = params->nth;
@@ -6827,16 +6698,6 @@ static void ggml_compute_forward_concat(
     const struct ggml_tensor * src0 = dst->src[0];
 
     switch (src0->type) {
-        case GGML_TYPE_F16:
-        case GGML_TYPE_BF16:
-        case GGML_TYPE_I16:
-            {
-                ggml_compute_forward_concat_f16(params, dst);
-            } break;
-        case GGML_TYPE_I8:
-            {
-                ggml_compute_forward_concat_i8(params, dst);
-            } break;
         case GGML_TYPE_F32:
         case GGML_TYPE_I32:
             {
@@ -6844,7 +6705,7 @@ static void ggml_compute_forward_concat(
             } break;
         default:
             {
-                ggml_compute_forward_concat_any(params, dst);
+                GGML_ABORT("fatal error");
             }
     }
 }

ggml/src/ggml-metal/CMakeLists.txt

@@ -88,8 +88,9 @@ else()
 
     add_custom_command(
         OUTPUT ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/default.metallib
-        COMMAND xcrun -sdk macosx metal ${XC_FLAGS} -c ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal.metal -o - |
-            xcrun -sdk macosx metallib - -o ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/default.metallib
+        COMMAND xcrun -sdk macosx metal    ${XC_FLAGS} -c ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal.metal -o ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal.air
+        COMMAND xcrun -sdk macosx metallib                ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal.air   -o ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/default.metallib
+        COMMAND rm -f ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal.air
         COMMAND rm -f ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-common.h
         COMMAND rm -f ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}/ggml-metal.metal
         DEPENDS ggml-metal.metal ${METALLIB_COMMON}

ggml/src/ggml.c

@@ -2332,7 +2332,6 @@ struct ggml_tensor * ggml_concat(
     struct ggml_tensor  * b,
     int                   dim) {
     GGML_ASSERT(dim >= 0 && dim < GGML_MAX_DIMS);
-    GGML_ASSERT(a->type == b->type);
 
     int64_t ne[GGML_MAX_DIMS];
     for (int d = 0; d < GGML_MAX_DIMS; ++d) {

scripts/sync-ggml.last

@@ -1 +1 @@
-c7dfe3d174f98b14801f9ed12f129179d3e7b638
+58ecf6b96d887e408b6869915863fa1126483d51