LLM inference in C/C++
C++ ggml
vulkan: add TQ1_0 support (mm, mat-vec, mat-vec-id, dequant, get_rows) (#27765)
Anjielon8fe90e1fbfc0
diff --git a/ggml/src/ggml-metal/ggml-metal-device.m b/ggml/src/ggml-metal/ggml-metal-device.mindex e20a4e8916..afd6f52101 100644--- a/ggml/src/ggml-metal/ggml-metal-device.m+++ b/ggml/src/ggml-metal/ggml-metal-device.m@@ -1486,7 +1486,9 @@ static bool ggml_metal_supports_mul_mat_op(const struct ggml_tensor * op,bool src0_f16_has_mv,bool mm_path) {- if (!has_simdgroup_reduction || op->src[0]->type == GGML_TYPE_NVFP4) {+ if (!has_simdgroup_reduction ||+ op->src[0]->type == GGML_TYPE_NVFP4 ||+ op->src[0]->type == GGML_TYPE_TQ1_0) {return false;}@@ -1887,7 +1889,8 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te};}case GGML_OP_GET_ROWS:- return op->src[0]->type != GGML_TYPE_NVFP4;+ return op->src[0]->type != GGML_TYPE_NVFP4 &&+ op->src[0]->type != GGML_TYPE_TQ1_0;case GGML_OP_SET_ROWS:{if (op->src[0]->type == GGML_TYPE_F16) {diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cppindex a04a6b27a8..efadd3663f 100644--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp@@ -4727,6 +4727,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {CREATE_MM2(pipeline_dequant_mul_mat_mat_f16[GGML_TYPE_Q8_0], matmul_q8_0_f16, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3)CREATE_MM2(pipeline_dequant_mul_mat_mat_f16[GGML_TYPE_Q2_K], matmul_q2_k_f16, mmq_wg_denoms_k, warptile_mmq_k, vk_mat_mat_push_constants, 3)CREATE_MM2(pipeline_dequant_mul_mat_mat_f16[GGML_TYPE_TQ2_0], matmul_tq2_0_f16, mmq_wg_denoms_k, warptile_mmq_k, vk_mat_mat_push_constants, 3)+ CREATE_MM2(pipeline_dequant_mul_mat_mat_f16[GGML_TYPE_TQ1_0], matmul_tq1_0_f16, mmq_wg_denoms_k, warptile_mmq_k, vk_mat_mat_push_constants, 3)CREATE_MM2(pipeline_dequant_mul_mat_mat_f16[GGML_TYPE_Q3_K], matmul_q3_k_f16, mmq_wg_denoms_k, warptile_mmq_k, vk_mat_mat_push_constants, 3)CREATE_MM2(pipeline_dequant_mul_mat_mat_f16[GGML_TYPE_Q4_K], matmul_q4_k_f16, mmq_wg_denoms_k, warptile_mmq_k, vk_mat_mat_push_constants, 3)CREATE_MM2(pipeline_dequant_mul_mat_mat_f16[GGML_TYPE_Q5_K], matmul_q5_k_f16, mmq_wg_denoms_k, warptile_mmq_k, vk_mat_mat_push_constants, 3)@@ -4768,6 +4769,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {CREATE_MM2(pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q8_0], matmul_id_subgroup_q8_0_f16, mmqid_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, 5)CREATE_MM2(pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q2_K], matmul_id_subgroup_q2_k_f16, mmqid_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, 5)CREATE_MM2(pipeline_dequant_mul_mat_mat_id[GGML_TYPE_TQ2_0], matmul_id_subgroup_tq2_0_f16, mmqid_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, 5)+ CREATE_MM2(pipeline_dequant_mul_mat_mat_id[GGML_TYPE_TQ1_0], matmul_id_subgroup_tq1_0_f16, mmqid_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, 5)CREATE_MM2(pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q3_K], matmul_id_subgroup_q3_k_f16, mmqid_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, 5)CREATE_MM2(pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q4_K], matmul_id_subgroup_q4_k_f16, mmqid_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, 5)CREATE_MM2(pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q5_K], matmul_id_subgroup_q5_k_f16, mmqid_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, 5)@@ -4841,6 +4843,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {CREATE_MM2(GGML_TYPE_Q2_K, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q2_K], matmul_q2_k_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, );CREATE_MM2(GGML_TYPE_TQ2_0, pipeline_dequant_mul_mat_mat[GGML_TYPE_TQ2_0], matmul_tq2_0_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, );+ CREATE_MM2(GGML_TYPE_TQ1_0, pipeline_dequant_mul_mat_mat[GGML_TYPE_TQ1_0], matmul_tq1_0_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, );CREATE_MM2(GGML_TYPE_Q3_K, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q3_K], matmul_q3_k_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, );CREATE_MM2(GGML_TYPE_Q4_K, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q4_K], matmul_q4_k_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, );CREATE_MM2(GGML_TYPE_Q5_K, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q5_K], matmul_q5_k_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, );@@ -4886,6 +4889,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {CREATE_MM2(GGML_TYPE_Q8_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q8_0], matmul_id_subgroup_q8_0_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id);CREATE_MM2(GGML_TYPE_Q2_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q2_K], matmul_id_subgroup_q2_k_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id);CREATE_MM2(GGML_TYPE_TQ2_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_TQ2_0], matmul_id_subgroup_tq2_0_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id);+ CREATE_MM2(GGML_TYPE_TQ1_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_TQ1_0], matmul_id_subgroup_tq1_0_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id);CREATE_MM2(GGML_TYPE_Q3_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q3_K], matmul_id_subgroup_q3_k_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id);CREATE_MM2(GGML_TYPE_Q4_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q4_K], matmul_id_subgroup_q4_k_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id);CREATE_MM2(GGML_TYPE_Q5_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q5_K], matmul_id_subgroup_q5_k_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id);@@ -4977,6 +4981,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {CREATE_MM2(GGML_TYPE_Q8_0, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q8_0], matmul_q8_0_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);CREATE_MM2(GGML_TYPE_Q2_K, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q2_K], matmul_q2_k_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);CREATE_MM2(GGML_TYPE_TQ2_0, pipeline_dequant_mul_mat_mat[GGML_TYPE_TQ2_0], matmul_tq2_0_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);+ CREATE_MM2(GGML_TYPE_TQ1_0, pipeline_dequant_mul_mat_mat[GGML_TYPE_TQ1_0], matmul_tq1_0_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);CREATE_MM2(GGML_TYPE_Q3_K, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q3_K], matmul_q3_k_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);CREATE_MM2(GGML_TYPE_Q4_K, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q4_K], matmul_q4_k_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);CREATE_MM2(GGML_TYPE_Q5_K, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q5_K], matmul_q5_k_f32, mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);@@ -5026,6 +5031,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {CREATE_MM2(GGML_TYPE_Q8_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q8_0], matmul_id_subgroup_q8_0_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);CREATE_MM2(GGML_TYPE_Q2_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q2_K], matmul_id_subgroup_q2_k_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);CREATE_MM2(GGML_TYPE_TQ2_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_TQ2_0], matmul_id_subgroup_tq2_0_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);+ CREATE_MM2(GGML_TYPE_TQ1_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_TQ1_0], matmul_id_subgroup_tq1_0_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);CREATE_MM2(GGML_TYPE_Q3_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q3_K], matmul_id_subgroup_q3_k_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);CREATE_MM2(GGML_TYPE_Q4_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q4_K], matmul_id_subgroup_q4_k_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);CREATE_MM2(GGML_TYPE_Q5_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q5_K], matmul_id_subgroup_q5_k_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);@@ -5074,6 +5080,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {CREATE_MM2(GGML_TYPE_Q8_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q8_0], matmul_id_q8_0_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);CREATE_MM2(GGML_TYPE_Q2_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q2_K], matmul_id_q2_k_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);CREATE_MM2(GGML_TYPE_TQ2_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_TQ2_0], matmul_id_tq2_0_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);+ CREATE_MM2(GGML_TYPE_TQ1_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_TQ1_0], matmul_id_tq1_0_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);CREATE_MM2(GGML_TYPE_Q3_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q3_K], matmul_id_q3_k_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);CREATE_MM2(GGML_TYPE_Q4_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q4_K], matmul_id_q4_k_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);CREATE_MM2(GGML_TYPE_Q5_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q5_K], matmul_id_q5_k_f32, mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);@@ -5154,6 +5161,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {CREATE_MM(GGML_TYPE_Q2_K, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q2_K].f32acc, matmul_q2_k_f32, , mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);CREATE_MM(GGML_TYPE_TQ2_0, pipeline_dequant_mul_mat_mat[GGML_TYPE_TQ2_0].f32acc, matmul_tq2_0_f32, , mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);+ CREATE_MM(GGML_TYPE_TQ1_0, pipeline_dequant_mul_mat_mat[GGML_TYPE_TQ1_0].f32acc, matmul_tq1_0_f32, , mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);CREATE_MM(GGML_TYPE_Q3_K, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q3_K].f32acc, matmul_q3_k_f32, , mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);CREATE_MM(GGML_TYPE_Q4_K, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q4_K].f32acc, matmul_q4_k_f32, , mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);CREATE_MM(GGML_TYPE_Q5_K, pipeline_dequant_mul_mat_mat[GGML_TYPE_Q5_K].f32acc, matmul_q5_k_f32, , mmq_wg_denoms, warptile_mmq, vk_mat_mat_push_constants, 3, , 0);@@ -5202,6 +5210,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {CREATE_MM(GGML_TYPE_Q8_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q8_0].f32acc, matmul_id_subgroup_q8_0_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);CREATE_MM(GGML_TYPE_Q2_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q2_K].f32acc, matmul_id_subgroup_q2_k_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);CREATE_MM(GGML_TYPE_TQ2_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_TQ2_0].f32acc, matmul_id_subgroup_tq2_0_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);+ CREATE_MM(GGML_TYPE_TQ1_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_TQ1_0].f32acc, matmul_id_subgroup_tq1_0_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);CREATE_MM(GGML_TYPE_Q3_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q3_K].f32acc, matmul_id_subgroup_q3_k_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);CREATE_MM(GGML_TYPE_Q4_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q4_K].f32acc, matmul_id_subgroup_q4_k_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);CREATE_MM(GGML_TYPE_Q5_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q5_K].f32acc, matmul_id_subgroup_q5_k_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, mul_mat_subgroup_size);@@ -5232,6 +5241,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {CREATE_MM(GGML_TYPE_Q8_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q8_0].f32acc, matmul_id_q8_0_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);CREATE_MM(GGML_TYPE_Q2_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q2_K].f32acc, matmul_id_q2_k_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);CREATE_MM(GGML_TYPE_TQ2_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_TQ2_0].f32acc, matmul_id_tq2_0_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);+ CREATE_MM(GGML_TYPE_TQ1_0, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_TQ1_0].f32acc, matmul_id_tq1_0_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);CREATE_MM(GGML_TYPE_Q3_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q3_K].f32acc, matmul_id_q3_k_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);CREATE_MM(GGML_TYPE_Q4_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q4_K].f32acc, matmul_id_q4_k_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);CREATE_MM(GGML_TYPE_Q5_K, pipeline_dequant_mul_mat_mat_id[GGML_TYPE_Q5_K].f32acc, matmul_id_q5_k_f32, , mmq_wg_denoms, warptile_mmqid, vk_mat_mat_id_push_constants, mul_mat_id_param_count, _id, 0);@@ -5341,6 +5351,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f32_f32[w][GGML_TYPE_Q8_0][i], "mul_mat_vec_q8_0_f32_f32", arr_dmmv_q8_0_f32_f32_len[reduc], arr_dmmv_q8_0_f32_f32_data[reduc], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {1*rm_stdq, 1, 1}, {wg_size_subgroup, 1*rm_stdq, i+1}, 1, true, use_subgroups, force_subgroup_size);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f32_f32[w][GGML_TYPE_Q2_K][i], "mul_mat_vec_q2_k_f32_f32", arr_dmmv_q2_k_f32_f32_len[reduc16], arr_dmmv_q2_k_f32_f32_data[reduc16], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq, i+1}, 1, true, use_subgroups16, force_subgroup_size16);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f32_f32[w][GGML_TYPE_TQ2_0][i], "mul_mat_vec_tq2_0_f32_f32", arr_dmmv_tq2_0_f32_f32_len[reduc16], arr_dmmv_tq2_0_f32_f32_data[reduc16], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq, i+1}, 1, true, use_subgroups16, force_subgroup_size16);+ ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f32_f32[w][GGML_TYPE_TQ1_0][i], "mul_mat_vec_tq1_0_f32_f32", arr_dmmv_tq1_0_f32_f32_len[reduc16], arr_dmmv_tq1_0_f32_f32_data[reduc16], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq, i+1}, 1, true, use_subgroups16, force_subgroup_size16);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f32_f32[w][GGML_TYPE_Q3_K][i], "mul_mat_vec_q3_k_f32_f32", arr_dmmv_q3_k_f32_f32_len[reduc16], arr_dmmv_q3_k_f32_f32_data[reduc16], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq, i+1}, 1, true, use_subgroups16, force_subgroup_size16);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f32_f32[w][GGML_TYPE_Q4_K][i], "mul_mat_vec_q4_k_f32_f32", arr_dmmv_q4_k_f32_f32_len[reduc16], arr_dmmv_q4_k_f32_f32_data[reduc16], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq, i+1}, 1, true, use_subgroups16, force_subgroup_size16);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f32_f32[w][GGML_TYPE_Q5_K][i], "mul_mat_vec_q5_k_f32_f32", arr_dmmv_q5_k_f32_f32_len[reduc16], arr_dmmv_q5_k_f32_f32_data[reduc16], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq, i+1}, 1, true, use_subgroups16, force_subgroup_size16);@@ -5369,6 +5380,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f16_f32[w][GGML_TYPE_Q8_0][i], "mul_mat_vec_q8_0_f16_f32", arr_dmmv_q8_0_f16_f32_len[reduc], arr_dmmv_q8_0_f16_f32_data[reduc], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {1*rm_stdq, 1, 1}, {wg_size_subgroup, 1*rm_stdq, i+1}, 1, true, use_subgroups, force_subgroup_size);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f16_f32[w][GGML_TYPE_Q2_K][i], "mul_mat_vec_q2_k_f16_f32", arr_dmmv_q2_k_f16_f32_len[reduc16], arr_dmmv_q2_k_f16_f32_data[reduc16], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq, i+1}, 1, true, use_subgroups16, force_subgroup_size16);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f16_f32[w][GGML_TYPE_TQ2_0][i], "mul_mat_vec_tq2_0_f16_f32", arr_dmmv_tq2_0_f16_f32_len[reduc16], arr_dmmv_tq2_0_f16_f32_data[reduc16], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq, i+1}, 1, true, use_subgroups16, force_subgroup_size16);+ ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f16_f32[w][GGML_TYPE_TQ1_0][i], "mul_mat_vec_tq1_0_f16_f32", arr_dmmv_tq1_0_f16_f32_len[reduc16], arr_dmmv_tq1_0_f16_f32_data[reduc16], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq, i+1}, 1, true, use_subgroups16, force_subgroup_size16);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f16_f32[w][GGML_TYPE_Q3_K][i], "mul_mat_vec_q3_k_f16_f32", arr_dmmv_q3_k_f16_f32_len[reduc16], arr_dmmv_q3_k_f16_f32_data[reduc16], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq, i+1}, 1, true, use_subgroups16, force_subgroup_size16);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f16_f32[w][GGML_TYPE_Q4_K][i], "mul_mat_vec_q4_k_f16_f32", arr_dmmv_q4_k_f16_f32_len[reduc16], arr_dmmv_q4_k_f16_f32_data[reduc16], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq, i+1}, 1, true, use_subgroups16, force_subgroup_size16);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_f16_f32[w][GGML_TYPE_Q5_K][i], "mul_mat_vec_q5_k_f16_f32", arr_dmmv_q5_k_f16_f32_len[reduc16], arr_dmmv_q5_k_f16_f32_data[reduc16], "main", mul_mat_vec_num_bindings, sizeof(vk_mat_vec_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq, i+1}, 1, true, use_subgroups16, force_subgroup_size16);@@ -5424,6 +5436,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_id_f32[w][GGML_TYPE_Q8_0], "mul_mat_vec_id_q8_0_f32", arr_dmmv_id_q8_0_f32_f32_len[reduc], arr_dmmv_id_q8_0_f32_f32_data[reduc], "main", mul_mat_vec_id_num_bindings, sizeof(vk_mat_vec_id_push_constants), {1*rm_stdq, 1, 1}, {wg_size_subgroup, 1*rm_stdq}, 1, true, use_subgroups, force_subgroup_size);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_id_f32[w][GGML_TYPE_Q2_K], "mul_mat_vec_id_q2_k_f32", arr_dmmv_id_q2_k_f32_f32_len[reduc16], arr_dmmv_id_q2_k_f32_f32_data[reduc16], "main", mul_mat_vec_id_num_bindings, sizeof(vk_mat_vec_id_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq}, 1, true, use_subgroups16, force_subgroup_size16);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_id_f32[w][GGML_TYPE_TQ2_0], "mul_mat_vec_id_tq2_0_f32", arr_dmmv_id_tq2_0_f32_f32_len[reduc16], arr_dmmv_id_tq2_0_f32_f32_data[reduc16], "main", mul_mat_vec_id_num_bindings, sizeof(vk_mat_vec_id_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq}, 1, true, use_subgroups16, force_subgroup_size16);+ ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_id_f32[w][GGML_TYPE_TQ1_0], "mul_mat_vec_id_tq1_0_f32", arr_dmmv_id_tq1_0_f32_f32_len[reduc16], arr_dmmv_id_tq1_0_f32_f32_data[reduc16], "main", mul_mat_vec_id_num_bindings, sizeof(vk_mat_vec_id_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq}, 1, true, use_subgroups16, force_subgroup_size16);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_id_f32[w][GGML_TYPE_Q3_K], "mul_mat_vec_id_q3_k_f32", arr_dmmv_id_q3_k_f32_f32_len[reduc16], arr_dmmv_id_q3_k_f32_f32_data[reduc16], "main", mul_mat_vec_id_num_bindings, sizeof(vk_mat_vec_id_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq}, 1, true, use_subgroups16, force_subgroup_size16);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_id_f32[w][GGML_TYPE_Q4_K], "mul_mat_vec_id_q4_k_f32", arr_dmmv_id_q4_k_f32_f32_len[reduc16], arr_dmmv_id_q4_k_f32_f32_data[reduc16], "main", mul_mat_vec_id_num_bindings, sizeof(vk_mat_vec_id_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq}, 1, true, use_subgroups16, force_subgroup_size16);ggml_vk_create_pipeline(device, device->pipeline_dequant_mul_mat_vec_id_f32[w][GGML_TYPE_Q5_K], "mul_mat_vec_id_q5_k_f32", arr_dmmv_id_q5_k_f32_f32_len[reduc16], arr_dmmv_id_q5_k_f32_f32_data[reduc16], "main", mul_mat_vec_id_num_bindings, sizeof(vk_mat_vec_id_push_constants), {rm_kq, 1, 1}, {wg_size_subgroup16, rm_kq}, 1, true, use_subgroups16, force_subgroup_size16);@@ -5490,6 +5503,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {ggml_vk_create_pipeline(device, device->pipeline_dequant_transpose[GGML_TYPE_Q8_0], "dequant_q8_0_transpose", dequant_q8_0_transpose_len, dequant_q8_0_transpose_data, "main", 2, 5 * sizeof(uint32_t), {256 * 16, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_dequant[GGML_TYPE_Q2_K], "dequant_q2_k", dequant_q2_k_len, dequant_q2_k_data, "main", 2, 5 * sizeof(uint32_t), {256 * 64, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_dequant[GGML_TYPE_TQ2_0], "dequant_tq2_0", dequant_tq2_0_len, dequant_tq2_0_data, "main", 2, 5 * sizeof(uint32_t), {256 * 64, 1, 1}, {}, 1);+ ggml_vk_create_pipeline(device, device->pipeline_dequant[GGML_TYPE_TQ1_0], "dequant_tq1_0", dequant_tq1_0_len, dequant_tq1_0_data, "main", 2, 5 * sizeof(uint32_t), {256 * 4, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_dequant[GGML_TYPE_Q3_K], "dequant_q3_k", dequant_q3_k_len, dequant_q3_k_data, "main", 2, 5 * sizeof(uint32_t), {256 * 64, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_dequant[GGML_TYPE_Q4_K], "dequant_q4_k", dequant_q4_k_len, dequant_q4_k_data, "main", 2, 5 * sizeof(uint32_t), {256 * 32, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_dequant[GGML_TYPE_Q5_K], "dequant_q5_k", dequant_q5_k_len, dequant_q5_k_data, "main", 2, 5 * sizeof(uint32_t), {256 * 64, 1, 1}, {}, 1);@@ -5519,6 +5533,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {ggml_vk_create_pipeline(device, device->pipeline_get_rows[GGML_TYPE_Q8_0], "get_rows_q8_0", get_rows_q8_0_len, get_rows_q8_0_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_get_rows[GGML_TYPE_Q2_K], "get_rows_q2_k", get_rows_q2_k_len, get_rows_q2_k_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_get_rows[GGML_TYPE_TQ2_0], "get_rows_tq2_0", get_rows_tq2_0_len, get_rows_tq2_0_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);+ ggml_vk_create_pipeline(device, device->pipeline_get_rows[GGML_TYPE_TQ1_0], "get_rows_tq1_0", get_rows_tq1_0_len, get_rows_tq1_0_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_get_rows[GGML_TYPE_Q3_K], "get_rows_q3_k", get_rows_q3_k_len, get_rows_q3_k_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_get_rows[GGML_TYPE_Q4_K], "get_rows_q4_k", get_rows_q4_k_len, get_rows_q4_k_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_get_rows[GGML_TYPE_Q5_K], "get_rows_q5_k", get_rows_q5_k_len, get_rows_q5_k_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);@@ -5548,6 +5563,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {ggml_vk_create_pipeline(device, device->pipeline_get_rows_f32[GGML_TYPE_Q8_0], "get_rows_q8_0_f32", get_rows_q8_0_f32_len, get_rows_q8_0_f32_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_get_rows_f32[GGML_TYPE_Q2_K], "get_rows_q2_k_f32", get_rows_q2_k_f32_len, get_rows_q2_k_f32_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_get_rows_f32[GGML_TYPE_TQ2_0], "get_rows_tq2_0_f32", get_rows_tq2_0_f32_len, get_rows_tq2_0_f32_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);+ ggml_vk_create_pipeline(device, device->pipeline_get_rows_f32[GGML_TYPE_TQ1_0], "get_rows_tq1_0_f32", get_rows_tq1_0_f32_len, get_rows_tq1_0_f32_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_get_rows_f32[GGML_TYPE_Q3_K], "get_rows_q3_k_f32", get_rows_q3_k_f32_len, get_rows_q3_k_f32_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_get_rows_f32[GGML_TYPE_Q4_K], "get_rows_q4_k_f32", get_rows_q4_k_f32_len, get_rows_q4_k_f32_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);ggml_vk_create_pipeline(device, device->pipeline_get_rows_f32[GGML_TYPE_Q5_K], "get_rows_q5_k_f32", get_rows_q5_k_f32_len, get_rows_q5_k_f32_data, "main", 3, sizeof(vk_op_binary_push_constants), {1024, 1, 1}, {}, 1);@@ -7787,6 +7803,7 @@ static vk_pipeline ggml_vk_get_to_fp16(ggml_backend_vk_context * ctx, ggml_typecase GGML_TYPE_MXFP4:case GGML_TYPE_NVFP4:case GGML_TYPE_TQ2_0:+ case GGML_TYPE_TQ1_0:break;default:return nullptr;@@ -7862,6 +7879,7 @@ static vk_matmul_pipeline ggml_vk_get_mul_mat_mat_pipeline(ggml_backend_vk_contecase GGML_TYPE_MXFP4:case GGML_TYPE_NVFP4:case GGML_TYPE_TQ2_0:+ case GGML_TYPE_TQ1_0:break;default:return nullptr;@@ -7932,6 +7950,7 @@ static vk_pipeline ggml_vk_get_dequantize_mul_mat_vec(ggml_backend_vk_context *case GGML_TYPE_MXFP4:case GGML_TYPE_NVFP4:case GGML_TYPE_TQ2_0:+ case GGML_TYPE_TQ1_0:break;default:return nullptr;@@ -8026,6 +8045,7 @@ static vk_matmul_pipeline ggml_vk_get_mul_mat_mat_id_pipeline(ggml_backend_vk_cocase GGML_TYPE_MXFP4:case GGML_TYPE_NVFP4:case GGML_TYPE_TQ2_0:+ case GGML_TYPE_TQ1_0:break;default:return nullptr;@@ -8099,6 +8119,7 @@ static vk_pipeline ggml_vk_get_dequantize_mul_mat_vec_id(ggml_backend_vk_contextcase GGML_TYPE_MXFP4:case GGML_TYPE_NVFP4:case GGML_TYPE_TQ2_0:+ case GGML_TYPE_TQ1_0:break;default:return nullptr;@@ -18673,6 +18694,7 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggmcase GGML_TYPE_MXFP4:case GGML_TYPE_NVFP4:case GGML_TYPE_TQ2_0:+ case GGML_TYPE_TQ1_0:break;default:return false;@@ -18779,6 +18801,7 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggmcase GGML_TYPE_MXFP4:case GGML_TYPE_NVFP4:case GGML_TYPE_TQ2_0:+ case GGML_TYPE_TQ1_0:case GGML_TYPE_I32:return true;default:diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs.glsl b/ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs.glslindex 627932bd35..9df66cb44f 100644--- a/ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs.glsl+++ b/ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs.glsl@@ -608,6 +608,21 @@ vec2 get_dm(uint ib, uint a_offset) {}#endif+#if defined(DATA_A_TQ1_0)+float tq1_0_val(uint ib, uint e, uint a_offset) {+ const uint bidx = tq1_0_byte_of(e);+ const uint qbyte = uint(bidx < 48u ? data_a[a_offset + ib].qs[bidx]+ : data_a[a_offset + ib].qh[bidx - 48u]);+ return float(tq1_0_trit(qbyte, tq1_0_digit_of(e))) - 1.0;+}+vec2 dequantize(uint ib, uint iqs, uint a_offset) {+ return vec2(tq1_0_val(ib, iqs, a_offset), tq1_0_val(ib, iqs + 1u, a_offset));+}+vec2 get_dm(uint ib, uint a_offset) {+ return vec2(float(data_a[a_offset + ib].d), 0);+}+#endif+#if defined(DATA_A_TQ2_0)vec2 dequantize(uint ib, uint iqs, uint a_offset) {// elem e -> byte qs[(e/128)*32 + e%32], bits 2*((e%128)/32); w = q - 1 (d applied via get_dm)diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs_cm2.glsl b/ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs_cm2.glslindex 46cc69cb26..ef53264a77 100644--- a/ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs_cm2.glsl+++ b/ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs_cm2.glsl@@ -247,6 +247,19 @@ f16vec4 dequantFuncQ8_0_v(const in decodeBufQ8_0 bl, const in uint blockCoords[2return f16vec4(vec4(qi) * vec4(float(d)));}+layout(buffer_reference, std430, buffer_reference_align = 2) buffer decodeBufTQ1_0 {+ block_tq1_0 block;+};++float16_t dequantFuncTQ1_0(const in decodeBufTQ1_0 bl, const in uint blockCoords[2], const in uint coordInBlock[2])+{+ const uint e = coordInBlock[1];+ const uint bidx = tq1_0_byte_of(e);+ const uint qbyte = uint(bidx < 48u ? bl.block.qs[bidx] : bl.block.qh[bidx - 48u]);+ const uint xi = tq1_0_trit(qbyte, tq1_0_digit_of(e));+ return bl.block.d * (float16_t(int(xi)) - float16_t(1.0));+}+layout(buffer_reference, std430, buffer_reference_align = 2) buffer decodeBufTQ2_0 {block_tq2_0 block;};@@ -1406,6 +1419,8 @@ f16vec4 dequantFuncNVFP4_v(const in decodeBufNVFP4 bl, const in uint blockCoords#elif defined(DATA_A_Q8_0)#define dequantFuncA dequantFuncQ8_0#define dequantFuncA_v dequantFuncQ8_0_v+#elif defined(DATA_A_TQ1_0)+#define dequantFuncA dequantFuncTQ1_0#elif defined(DATA_A_TQ2_0)#define dequantFuncA dequantFuncTQ2_0#define dequantFuncA_v dequantFuncTQ2_0_vdiff --git a/ggml/src/ggml-vulkan/vulkan-shaders/dequant_tq1_0.comp b/ggml/src/ggml-vulkan/vulkan-shaders/dequant_tq1_0.compnew file mode 100644index 0000000000..1632e74631--- /dev/null+++ b/ggml/src/ggml-vulkan/vulkan-shaders/dequant_tq1_0.comp@@ -0,0 +1,28 @@+#version 450++#include "dequant_head.glsl"++layout (local_size_x = 256, local_size_y = 1, local_size_z = 1) in;++layout (binding = 0) readonly buffer A {block_tq1_0 data_a[];};+layout (binding = 1) writeonly buffer D {D_TYPE data_b[];};++void main() {+ const uint i = gl_GlobalInvocationID.x * 4;++ if (i >= p.nel) {+ return;+ }++ const uint ib = i / QUANT_K_TQ1_0;+ const float d = float(data_a[ib].d);++ [[unroll]] for (uint j = 0; j < 4 && (i + j) < p.nel; ++j) {+ const uint e = (i + j) % QUANT_K_TQ1_0;+ const uint bidx = tq1_0_byte_of(e);+ const uint qbyte = uint(bidx < 48u ? data_a[ib].qs[bidx]+ : data_a[ib].qh[bidx - 48u]);+ const uint xi = tq1_0_trit(qbyte, tq1_0_digit_of(e));+ data_b[i + j] = D_TYPE(d * (float(xi) - 1.0f));+ }+}diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_tq1_0.comp b/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_tq1_0.compnew file mode 100644index 0000000000..2c99a268e6--- /dev/null+++ b/ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_tq1_0.comp@@ -0,0 +1,85 @@+#version 450+#extension GL_EXT_shader_explicit_arithmetic_types : require++#include "mul_mat_vec_base.glsl"++layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;++FLOAT_TYPE temp[NUM_COLS][NUM_ROWS];++// Walks the packed bytes directly (byte m, digit t) rather than via+// tq1_0_byte_of()/tq1_0_digit_of(): one byte per thread, expanded in place.+void compute_outputs(const uint32_t first_row, const uint32_t num_rows) {+ uint a_offset, b_offset, d_offset;+ get_offsets(a_offset, b_offset, d_offset);++ const uint num_blocks_per_row = p.ncols / QUANT_K;+ const uint tid = gl_LocalInvocationID.x;++ [[unroll]] for (uint j = 0; j < NUM_COLS; ++j) {+ [[unroll]] for (uint i = 0; i < NUM_ROWS; ++i) {+ temp[j][i] = FLOAT_TYPE(0);+ }+ }++ for (uint nrow = 0; nrow < num_rows; ++nrow) {+ const uint ib0 = a_offset + (first_row + nrow) * num_blocks_per_row;+ for (uint jcol = 0; jcol < NUM_COLS; ++jcol) {+ const uint b_base = (jcol * p.batch_stride_b);+ for (uint i = tid/8; i < num_blocks_per_row; i += gl_WorkGroupSize.x/8) {+ const FLOAT_TYPE d = float(data_a[ib0 + i].d);++ // First qs chunk: 32 bytes (5*32 elements)+ [[unroll]] for (uint m = tid%8; m < 32; m += 8) {+ const uint q_byte = uint(data_a[ib0 + i].qs[m]);+ [[unroll]] for (uint t = 0; t < 5; ++t) {+ const uint xi = tq1_0_trit(q_byte, t);+ const FLOAT_TYPE dequant_val = FLOAT_TYPE(d * (float(xi) - 1.0f));+ const uint elem = t * 32u + m;+ const uint b_idx = i * QUANT_K + elem;+ temp[jcol][nrow] += dequant_val * FLOAT_TYPE(data_b[b_base + b_offset + b_idx]);+ }+ }++ // Second qs chunk: 16 bytes (5*16 elements)+ [[unroll]] for (uint m = tid%8; m < 16; m += 8) {+ const uint q_byte = uint(data_a[ib0 + i].qs[32u + m]);+ [[unroll]] for (uint t = 0; t < 5; ++t) {+ const uint xi = tq1_0_trit(q_byte, t);+ const FLOAT_TYPE dequant_val = FLOAT_TYPE(d * (float(xi) - 1.0f));+ const uint elem = 160u + t * 16u + m;+ const uint b_idx = i * QUANT_K + elem;+ temp[jcol][nrow] += dequant_val * FLOAT_TYPE(data_b[b_base + b_offset + b_idx]);+ }+ }++ // qh bytes: 4 bytes (4*4 elements)+ [[unroll]] for (uint j = tid%8; j < 4; j += 8) {+ const uint qh_byte = uint(data_a[ib0 + i].qh[j]);+ [[unroll]] for (uint t = 0; t < 4; ++t) {+ const uint xi = tq1_0_trit(qh_byte, t);+ const FLOAT_TYPE dequant_val = FLOAT_TYPE(d * (float(xi) - 1.0f));+ const uint elem = 240u + t * 4u + j;+ const uint b_idx = i * QUANT_K + elem;+ temp[jcol][nrow] += dequant_val * FLOAT_TYPE(data_b[b_base + b_offset + b_idx]);+ }+ }+ }+ }+ }++ reduce_result(temp, d_offset, first_row, num_rows, tid);+}++void main() {+ const uint first_row = NUM_ROWS * (gl_WorkGroupID.x + gl_NumWorkGroups.x * gl_WorkGroupID.z);++ if (first_row + NUM_ROWS <= p.stride_d) {+ compute_outputs(first_row, NUM_ROWS);+ } else {+ if (first_row >= p.stride_d) {+ return;+ }+ compute_outputs(first_row, p.stride_d - first_row);+ }+}diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/mul_mm_funcs.glsl b/ggml/src/ggml-vulkan/vulkan-shaders/mul_mm_funcs.glslindex 7d852dced8..bdc70af140 100644--- a/ggml/src/ggml-vulkan/vulkan-shaders/mul_mm_funcs.glsl+++ b/ggml/src/ggml-vulkan/vulkan-shaders/mul_mm_funcs.glsl@@ -197,6 +197,24 @@ void load_a_to_shmem(const uint pos_a, const uint row, const uint col, const uinconst uint k_pair = row * LOAD_VEC_A / 2;store_a(col, k_pair, FLOAT_TYPEV2(v.xy));store_a(col, k_pair + 1, FLOAT_TYPEV2(v.zw));+#elif defined(DATA_A_TQ1_0)+ const uint idx = pos_a + col * p.stride_a / LOAD_VEC_A + row;++ const uint ib = idx / 128; // 2 values per idx+ const uint iqs = (idx % 128) * 2; // element 0,2,4..254++ const float d = float(data_a[ib].d);+ vec2 v;+ for (uint kk = 0u; kk < 2u; ++kk) {+ const uint e = iqs + kk;+ const uint bidx = tq1_0_byte_of(e);+ const uint qbyte = uint(bidx < 48u ? data_a[ib].qs[bidx]+ : data_a[ib].qh[bidx - 48u]);+ v[kk] = d * (float(tq1_0_trit(qbyte, tq1_0_digit_of(e))) - 1.0);+ }++ const uint k_pair = row * LOAD_VEC_A / 2;+ store_a(col, k_pair, FLOAT_TYPEV2(v.xy));#elif defined(DATA_A_TQ2_0)const uint idx = pos_a + col * p.stride_a / LOAD_VEC_A + row;diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/types.glsl b/ggml/src/ggml-vulkan/vulkan-shaders/types.glslindex adb1bb8b32..a19c7f2f4e 100644--- a/ggml/src/ggml-vulkan/vulkan-shaders/types.glsl+++ b/ggml/src/ggml-vulkan/vulkan-shaders/types.glsl@@ -303,6 +303,41 @@ struct block_q2_K_packed32#define DATA_A_QUANT_K#endif+#define QUANT_K_TQ1_0 256++// TQ1_0: base-3 packed trits, 5 per byte in `qs` (48B) and 4 in `qh` (4B).+struct block_tq1_0+{+ uint8_t qs[(QUANT_K_TQ1_0 - 4 * QUANT_K_TQ1_0 / 64) / 5];+ uint8_t qh[QUANT_K_TQ1_0 / 64];+ float16_t d;+};++// Element e in [0,255] -> its packed byte (0..47 qs, 48..51 qh) and digit.+uint tq1_0_byte_of(uint e) {+ return e < 160u ? (e % 32u)+ : e < 240u ? 32u + ((e - 160u) % 16u)+ : 48u + ((e - 240u) % 4u);+}+uint tq1_0_digit_of(uint e) {+ return e < 160u ? (e / 32u)+ : e < 240u ? ((e - 160u) / 16u)+ : ((e - 240u) / 4u);+}+// The 8-bit truncation below is part of the format, not an optimisation:+// the C reference does `uint8_t q = qs[..] * pow3[n]`.+uint tq1_0_trit(uint qbyte, uint t) {+ const uint POW3_PACKED = (1u << 28) | (3u << 21) | (9u << 14) | (27u << 7) | 81u;+ return ((((qbyte * ((POW3_PACKED >> (7u * (4u - t))) & 0x7Fu)) & 255u) * 3u) >> 8);+}++#if defined(DATA_A_TQ1_0)+#define QUANT_K QUANT_K_TQ1_0+#define QUANT_R 1+#define A_TYPE block_tq1_0+#define DATA_A_QUANT_K+#endif+#define QUANT_K_TQ2_0 256// ternary (BitNet): 2-bit codes, w = (q - 1) * d; qs layout matches q2_K'sdiff --git a/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp b/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cppindex 27ff68c10d..5d4b9c5fa4 100644--- a/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp+++ b/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp@@ -72,6 +72,7 @@ const std::vector<std::string> type_names = {"iq4_nl","mxfp4","nvfp4",+ "tq1_0","tq2_0","bf16",};@@ -734,7 +735,7 @@ void process_shaders() {for (const auto& tname : type_names) {// mul mat vecstd::string data_a_key = "DATA_A_" + to_uppercase(tname);- std::string shader = (string_ends_with(tname, "_k") || string_starts_with(tname, "iq1_") || string_starts_with(tname, "iq2_") || string_starts_with(tname, "iq3_") || tname == "tq2_0") ? "mul_mat_vec_" + tname + ".comp" : "mul_mat_vec.comp";+ std::string shader = (string_ends_with(tname, "_k") || string_starts_with(tname, "iq1_") || string_starts_with(tname, "iq2_") || string_starts_with(tname, "iq3_") || tname == "tq2_0" || tname == "tq1_0") ? "mul_mat_vec_" + tname + ".comp" : "mul_mat_vec.comp";string_to_spv("mul_mat_vec_" + tname + "_f32_f32", shader, merge_maps(base_dict, {{data_a_key, "1"}, {"B_TYPE", "float"}, {"B_TYPEV2", "vec2"}, {"B_TYPEV4", "vec4"}, {"D_TYPE", "float"}}));string_to_spv("mul_mat_vec_" + tname + "_f16_f32", shader, merge_maps(base_dict, {{data_a_key, "1"}, {"B_TYPE", "float16_t"}, {"B_TYPEV2", "f16vec2"}, {"B_TYPEV4", "f16vec4"}, {"D_TYPE", "float"}}));diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cppindex c93e41b2e2..31593541f5 100644--- a/tests/test-backend-ops.cpp+++ b/tests/test-backend-ops.cpp@@ -8646,7 +8646,7 @@ static const ggml_type all_types[] = {GGML_TYPE_Q4_K, GGML_TYPE_Q5_K,GGML_TYPE_Q6_K,GGML_TYPE_TQ2_0,- // GGML_TYPE_TQ1_0, // TODO: implement for all backends+ GGML_TYPE_TQ1_0,GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S,GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M,GGML_TYPE_IQ4_NL, GGML_TYPE_IQ3_S, GGML_TYPE_IQ4_XS,@@ -8674,7 +8674,7 @@ static const ggml_type other_types[] = {GGML_TYPE_Q5_K,GGML_TYPE_Q6_K,GGML_TYPE_TQ2_0,- // GGML_TYPE_TQ1_0, // TODO: implement for all backends+ GGML_TYPE_TQ1_0,GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S,GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M,GGML_TYPE_IQ4_NL, GGML_TYPE_IQ3_S, GGML_TYPE_IQ4_XS,@@ -9815,6 +9815,11 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_MXFP4, GGML_TYPE_F32, 32, 2, false, 2880, 32, 2880));test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_Q4_0, GGML_TYPE_F32, 32, 2, false, 2880, 32, 2880));+ // multiple blocks per row: exercises the block-stride loop and the+ // per-expert base offset, which k == 256 alone leaves untested+ test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_TQ1_0, GGML_TYPE_F32, 28, 10, false, 1024, 1, 4096));+ test_cases.emplace_back(new test_mul_mat_id(GGML_TYPE_TQ1_0, GGML_TYPE_F32, 128, 8, false, 1024, 1, 2048));+for (ggml_type type_a : all_types) {test_cases.emplace_back(new test_mul_mat_id(type_a, GGML_TYPE_F32, 4, 2, false, 64, 16, 3*ggml_blck_size(type_a)));}