From 503983a69a3107a70dc42b69164665743861fb28 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Wed, 14 Aug 2024 10:29:23 +0300 Subject: [PATCH] cuda : build only necessary templates --- ggml/src/ggml-cuda/fattn.cu | 12 --- ggml/src/ggml-cuda/mmq.cu | 90 +++++++++---------- ggml/src/ggml-cuda/mmq.cuh | 30 +++---- .../fattn-vec-f16-instance-hs128-f16-q4_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-f16-q4_1.cu | 5 -- .../fattn-vec-f16-instance-hs128-f16-q5_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-f16-q5_1.cu | 5 -- .../fattn-vec-f16-instance-hs128-f16-q8_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q4_0-f16.cu | 5 -- .../fattn-vec-f16-instance-hs128-q4_0-q4_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q4_0-q4_1.cu | 5 -- .../fattn-vec-f16-instance-hs128-q4_0-q5_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q4_0-q5_1.cu | 5 -- .../fattn-vec-f16-instance-hs128-q4_0-q8_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q4_1-f16.cu | 5 -- .../fattn-vec-f16-instance-hs128-q4_1-q4_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q4_1-q4_1.cu | 5 -- .../fattn-vec-f16-instance-hs128-q4_1-q5_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q4_1-q5_1.cu | 5 -- .../fattn-vec-f16-instance-hs128-q4_1-q8_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q5_0-f16.cu | 5 -- .../fattn-vec-f16-instance-hs128-q5_0-q4_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q5_0-q4_1.cu | 5 -- .../fattn-vec-f16-instance-hs128-q5_0-q5_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q5_0-q5_1.cu | 5 -- .../fattn-vec-f16-instance-hs128-q5_0-q8_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q5_1-f16.cu | 5 -- .../fattn-vec-f16-instance-hs128-q5_1-q4_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q5_1-q4_1.cu | 5 -- .../fattn-vec-f16-instance-hs128-q5_1-q5_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q5_1-q5_1.cu | 5 -- .../fattn-vec-f16-instance-hs128-q5_1-q8_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q8_0-f16.cu | 5 -- .../fattn-vec-f16-instance-hs128-q8_0-q4_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q8_0-q4_1.cu | 5 -- .../fattn-vec-f16-instance-hs128-q8_0-q5_0.cu | 5 -- .../fattn-vec-f16-instance-hs128-q8_0-q5_1.cu | 5 -- .../fattn-vec-f16-instance-hs128-q8_0-q8_0.cu | 5 -- .../fattn-vec-f16-instance-hs256-f16-f16.cu | 5 -- .../fattn-vec-f16-instance-hs64-f16-f16.cu | 5 -- .../fattn-vec-f16-instance-hs64-f16-q4_0.cu | 5 -- .../fattn-vec-f16-instance-hs64-f16-q4_1.cu | 5 -- .../fattn-vec-f16-instance-hs64-f16-q5_0.cu | 5 -- .../fattn-vec-f16-instance-hs64-f16-q5_1.cu | 5 -- .../fattn-vec-f16-instance-hs64-f16-q8_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-f16-q4_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-f16-q4_1.cu | 5 -- .../fattn-vec-f32-instance-hs128-f16-q5_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-f16-q5_1.cu | 5 -- .../fattn-vec-f32-instance-hs128-f16-q8_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q4_0-f16.cu | 5 -- .../fattn-vec-f32-instance-hs128-q4_0-q4_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q4_0-q4_1.cu | 5 -- .../fattn-vec-f32-instance-hs128-q4_0-q5_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q4_0-q5_1.cu | 5 -- .../fattn-vec-f32-instance-hs128-q4_0-q8_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q4_1-f16.cu | 5 -- .../fattn-vec-f32-instance-hs128-q4_1-q4_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q4_1-q4_1.cu | 5 -- .../fattn-vec-f32-instance-hs128-q4_1-q5_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q4_1-q5_1.cu | 5 -- .../fattn-vec-f32-instance-hs128-q4_1-q8_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q5_0-f16.cu | 5 -- .../fattn-vec-f32-instance-hs128-q5_0-q4_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q5_0-q4_1.cu | 5 -- .../fattn-vec-f32-instance-hs128-q5_0-q5_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q5_0-q5_1.cu | 5 -- .../fattn-vec-f32-instance-hs128-q5_0-q8_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q5_1-f16.cu | 5 -- .../fattn-vec-f32-instance-hs128-q5_1-q4_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q5_1-q4_1.cu | 5 -- .../fattn-vec-f32-instance-hs128-q5_1-q5_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q5_1-q5_1.cu | 5 -- .../fattn-vec-f32-instance-hs128-q5_1-q8_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q8_0-f16.cu | 5 -- .../fattn-vec-f32-instance-hs128-q8_0-q4_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q8_0-q4_1.cu | 5 -- .../fattn-vec-f32-instance-hs128-q8_0-q5_0.cu | 5 -- .../fattn-vec-f32-instance-hs128-q8_0-q5_1.cu | 5 -- .../fattn-vec-f32-instance-hs128-q8_0-q8_0.cu | 5 -- .../fattn-vec-f32-instance-hs256-f16-f16.cu | 5 -- .../fattn-vec-f32-instance-hs64-f16-f16.cu | 5 -- .../fattn-vec-f32-instance-hs64-f16-q4_0.cu | 5 -- .../fattn-vec-f32-instance-hs64-f16-q4_1.cu | 5 -- .../fattn-vec-f32-instance-hs64-f16-q5_0.cu | 5 -- .../fattn-vec-f32-instance-hs64-f16-q5_1.cu | 5 -- .../fattn-vec-f32-instance-hs64-f16-q8_0.cu | 5 -- .../template-instances/mmq-instance-iq1_s.cu | 5 -- .../template-instances/mmq-instance-iq2_s.cu | 5 -- .../template-instances/mmq-instance-iq2_xs.cu | 5 -- .../mmq-instance-iq2_xxs.cu | 5 -- .../template-instances/mmq-instance-iq3_s.cu | 5 -- .../mmq-instance-iq3_xxs.cu | 5 -- .../template-instances/mmq-instance-iq4_nl.cu | 5 -- .../template-instances/mmq-instance-iq4_xs.cu | 5 -- .../template-instances/mmq-instance-q2_k.cu | 5 -- .../template-instances/mmq-instance-q3_k.cu | 5 -- .../template-instances/mmq-instance-q4_0.cu | 5 -- .../template-instances/mmq-instance-q4_1.cu | 5 -- .../template-instances/mmq-instance-q5_0.cu | 5 -- .../template-instances/mmq-instance-q5_1.cu | 5 -- .../template-instances/mmq-instance-q5_k.cu | 5 -- 102 files changed, 60 insertions(+), 567 deletions(-) delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs256-f16-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs256-f16-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q8_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-iq1_s.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_s.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xs.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xxs.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_s.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_xxs.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-q2_k.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-q3_k.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-q4_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-q4_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-q5_0.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-q5_1.cu delete mode 100644 ggml/src/ggml-cuda/template-instances/mmq-instance-q5_k.cu diff --git a/ggml/src/ggml-cuda/fattn.cu b/ggml/src/ggml-cuda/fattn.cu index 29f608b0ff..8e939250b1 100644 --- a/ggml/src/ggml-cuda/fattn.cu +++ b/ggml/src/ggml-cuda/fattn.cu @@ -208,13 +208,7 @@ static void ggml_cuda_flash_attn_ext_vec_f16(ggml_backend_cuda_context & ctx, gg FATTN_VEC_F16_CASE(256, GGML_TYPE_F16, GGML_TYPE_F16) #else - FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_0) - - FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0) - - FATTN_VEC_F16_CASE( 64, GGML_TYPE_F16, GGML_TYPE_F16) FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_F16) - FATTN_VEC_F16_CASE(256, GGML_TYPE_F16, GGML_TYPE_F16) #endif // GGML_CUDA_FA_ALL_QUANTS on_no_fattn_vec_case(Q->ne[0]); @@ -283,13 +277,7 @@ static void ggml_cuda_flash_attn_ext_vec_f32(ggml_backend_cuda_context & ctx, gg FATTN_VEC_F32_CASE(256, GGML_TYPE_F16, GGML_TYPE_F16) #else - FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_0) - - FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0) - - FATTN_VEC_F32_CASE( 64, GGML_TYPE_F16, GGML_TYPE_F16) FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_F16) - FATTN_VEC_F32_CASE(256, GGML_TYPE_F16, GGML_TYPE_F16) #endif // GGML_CUDA_FA_ALL_QUANTS on_no_fattn_vec_case(Q->ne[0]); diff --git a/ggml/src/ggml-cuda/mmq.cu b/ggml/src/ggml-cuda/mmq.cu index 78d70cd7a4..66036bdd11 100644 --- a/ggml/src/ggml-cuda/mmq.cu +++ b/ggml/src/ggml-cuda/mmq.cu @@ -29,60 +29,60 @@ void ggml_cuda_op_mul_mat_q( const mmq_args args = {src0_dd_i, src1_ddq_i, dst_dd_i, ne00, row_diff, stride00, src1_padded_row_size, src1_ncols, ne11, nrows_dst}; switch (src0->type) { - case GGML_TYPE_Q4_0: - mul_mat_q_case(ctx, args, stream); - break; - case GGML_TYPE_Q4_1: - mul_mat_q_case(ctx, args, stream); - break; - case GGML_TYPE_Q5_0: - mul_mat_q_case(ctx, args, stream); - break; - case GGML_TYPE_Q5_1: - mul_mat_q_case(ctx, args, stream); - break; +// case GGML_TYPE_Q4_0: +// mul_mat_q_case(ctx, args, stream); +// break; +// case GGML_TYPE_Q4_1: +// mul_mat_q_case(ctx, args, stream); +// break; +// case GGML_TYPE_Q5_0: +// mul_mat_q_case(ctx, args, stream); +// break; +// case GGML_TYPE_Q5_1: +// mul_mat_q_case(ctx, args, stream); +// break; case GGML_TYPE_Q8_0: mul_mat_q_case(ctx, args, stream); break; - case GGML_TYPE_Q2_K: - mul_mat_q_case(ctx, args, stream); - break; - case GGML_TYPE_Q3_K: - mul_mat_q_case(ctx, args, stream); - break; +// case GGML_TYPE_Q2_K: +// mul_mat_q_case(ctx, args, stream); +// break; +// case GGML_TYPE_Q3_K: +// mul_mat_q_case(ctx, args, stream); +// break; case GGML_TYPE_Q4_K: mul_mat_q_case(ctx, args, stream); break; - case GGML_TYPE_Q5_K: - mul_mat_q_case(ctx, args, stream); - break; +// case GGML_TYPE_Q5_K: +// mul_mat_q_case(ctx, args, stream); +// break; case GGML_TYPE_Q6_K: mul_mat_q_case(ctx, args, stream); break; - case GGML_TYPE_IQ2_XXS: - mul_mat_q_case(ctx, args, stream); - break; - case GGML_TYPE_IQ2_XS: - mul_mat_q_case(ctx, args, stream); - break; - case GGML_TYPE_IQ2_S: - mul_mat_q_case(ctx, args, stream); - break; - case GGML_TYPE_IQ3_XXS: - mul_mat_q_case(ctx, args, stream); - break; - case GGML_TYPE_IQ3_S: - mul_mat_q_case(ctx, args, stream); - break; - case GGML_TYPE_IQ1_S: - mul_mat_q_case(ctx, args, stream); - break; - case GGML_TYPE_IQ4_XS: - mul_mat_q_case(ctx, args, stream); - break; - case GGML_TYPE_IQ4_NL: - mul_mat_q_case(ctx, args, stream); - break; +// case GGML_TYPE_IQ2_XXS: +// mul_mat_q_case(ctx, args, stream); +// break; +// case GGML_TYPE_IQ2_XS: +// mul_mat_q_case(ctx, args, stream); +// break; +// case GGML_TYPE_IQ2_S: +// mul_mat_q_case(ctx, args, stream); +// break; +// case GGML_TYPE_IQ3_XXS: +// mul_mat_q_case(ctx, args, stream); +// break; +// case GGML_TYPE_IQ3_S: +// mul_mat_q_case(ctx, args, stream); +// break; +// case GGML_TYPE_IQ1_S: +// mul_mat_q_case(ctx, args, stream); +// break; +// case GGML_TYPE_IQ4_XS: +// mul_mat_q_case(ctx, args, stream); +// break; +// case GGML_TYPE_IQ4_NL: +// mul_mat_q_case(ctx, args, stream); +// break; default: GGML_ABORT("fatal error"); break; diff --git a/ggml/src/ggml-cuda/mmq.cuh b/ggml/src/ggml-cuda/mmq.cuh index e8a957447d..b4a31b982c 100644 --- a/ggml/src/ggml-cuda/mmq.cuh +++ b/ggml/src/ggml-cuda/mmq.cuh @@ -2906,24 +2906,24 @@ void mul_mat_q_case(ggml_backend_cuda_context & ctx, const mmq_args & args, cuda #define DECL_MMQ_CASE(type) \ template void mul_mat_q_case(ggml_backend_cuda_context & ctx, const mmq_args & args, cudaStream_t stream) \ -extern DECL_MMQ_CASE(GGML_TYPE_Q4_0); -extern DECL_MMQ_CASE(GGML_TYPE_Q4_1); -extern DECL_MMQ_CASE(GGML_TYPE_Q5_0); -extern DECL_MMQ_CASE(GGML_TYPE_Q5_1); +//extern DECL_MMQ_CASE(GGML_TYPE_Q4_0); +//extern DECL_MMQ_CASE(GGML_TYPE_Q4_1); +//extern DECL_MMQ_CASE(GGML_TYPE_Q5_0); +//extern DECL_MMQ_CASE(GGML_TYPE_Q5_1); extern DECL_MMQ_CASE(GGML_TYPE_Q8_0); -extern DECL_MMQ_CASE(GGML_TYPE_Q2_K); -extern DECL_MMQ_CASE(GGML_TYPE_Q3_K); +//extern DECL_MMQ_CASE(GGML_TYPE_Q2_K); +//extern DECL_MMQ_CASE(GGML_TYPE_Q3_K); extern DECL_MMQ_CASE(GGML_TYPE_Q4_K); -extern DECL_MMQ_CASE(GGML_TYPE_Q5_K); +//extern DECL_MMQ_CASE(GGML_TYPE_Q5_K); extern DECL_MMQ_CASE(GGML_TYPE_Q6_K); -extern DECL_MMQ_CASE(GGML_TYPE_IQ2_XXS); -extern DECL_MMQ_CASE(GGML_TYPE_IQ2_XS); -extern DECL_MMQ_CASE(GGML_TYPE_IQ2_S); -extern DECL_MMQ_CASE(GGML_TYPE_IQ3_XXS); -extern DECL_MMQ_CASE(GGML_TYPE_IQ3_S); -extern DECL_MMQ_CASE(GGML_TYPE_IQ1_S); -extern DECL_MMQ_CASE(GGML_TYPE_IQ4_NL); -extern DECL_MMQ_CASE(GGML_TYPE_IQ4_XS); +//extern DECL_MMQ_CASE(GGML_TYPE_IQ2_XXS); +//extern DECL_MMQ_CASE(GGML_TYPE_IQ2_XS); +//extern DECL_MMQ_CASE(GGML_TYPE_IQ2_S); +//extern DECL_MMQ_CASE(GGML_TYPE_IQ3_XXS); +//extern DECL_MMQ_CASE(GGML_TYPE_IQ3_S); +//extern DECL_MMQ_CASE(GGML_TYPE_IQ1_S); +//extern DECL_MMQ_CASE(GGML_TYPE_IQ4_NL); +//extern DECL_MMQ_CASE(GGML_TYPE_IQ4_XS); // ------------------------------------------------------------------------------------------------------------------------- diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_0.cu deleted file mode 100644 index dd070db285..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_1.cu deleted file mode 100644 index 54dcde6f52..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_0.cu deleted file mode 100644 index 4ec22f7919..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_1.cu deleted file mode 100644 index 3c15bf7f0e..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q8_0.cu deleted file mode 100644 index 7e61b5fdcd..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-f16.cu deleted file mode 100644 index fdb15b580c..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu deleted file mode 100644 index 0f7c417d2c..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_1.cu deleted file mode 100644 index 851f33c43f..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_0.cu deleted file mode 100644 index 763809cbeb..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_1.cu deleted file mode 100644 index f2a276e50e..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q8_0.cu deleted file mode 100644 index cb227f6f5c..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-f16.cu deleted file mode 100644 index 97ac0520c7..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_0.cu deleted file mode 100644 index c772b42634..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_1.cu deleted file mode 100644 index 5cb7430819..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_0.cu deleted file mode 100644 index 98a709d171..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_1.cu deleted file mode 100644 index 4f2f947ae8..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q8_0.cu deleted file mode 100644 index 11f96b6f65..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-f16.cu deleted file mode 100644 index b39bdc0611..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_0.cu deleted file mode 100644 index bbd6a2c7f4..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_1.cu deleted file mode 100644 index 9d84ff2b19..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_0.cu deleted file mode 100644 index bc8a5bff68..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_1.cu deleted file mode 100644 index a679100c83..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q8_0.cu deleted file mode 100644 index 8f21bccf7f..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-f16.cu deleted file mode 100644 index 858b00fd74..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_0.cu deleted file mode 100644 index 0fc8011fac..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_1.cu deleted file mode 100644 index 261fdf623e..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_0.cu deleted file mode 100644 index 0fb8247383..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_1.cu deleted file mode 100644 index a9d9d089bd..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q8_0.cu deleted file mode 100644 index 7d7b27920a..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-f16.cu deleted file mode 100644 index a092ee2d50..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_0.cu deleted file mode 100644 index db55927a19..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_1.cu deleted file mode 100644 index c3c21cefae..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_0.cu deleted file mode 100644 index 35dd9f5208..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_1.cu deleted file mode 100644 index 050c22ac7c..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q8_0.cu deleted file mode 100644 index de4866c5e6..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs256-f16-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs256-f16-f16.cu deleted file mode 100644 index 57a10bc4be..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs256-f16-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(256, GGML_TYPE_F16, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-f16.cu deleted file mode 100644 index e0f08b46a7..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(64, GGML_TYPE_F16, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_0.cu deleted file mode 100644 index 1c8e8a467a..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_1.cu deleted file mode 100644 index cefed83fb9..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_0.cu deleted file mode 100644 index aede6e3588..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_1.cu deleted file mode 100644 index 1a1a92c788..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q8_0.cu deleted file mode 100644 index ad667473d1..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f16.cuh" - -DECL_FATTN_VEC_F16_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_0.cu deleted file mode 100644 index 8286ebf373..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_1.cu deleted file mode 100644 index 4587868825..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_0.cu deleted file mode 100644 index d89103ce0c..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_1.cu deleted file mode 100644 index bb75fd42ff..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q8_0.cu deleted file mode 100644 index b1629817e7..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-f16.cu deleted file mode 100644 index d8657604da..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu deleted file mode 100644 index 2e5bd2f1a3..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_1.cu deleted file mode 100644 index be5f302d9f..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_0.cu deleted file mode 100644 index 8dd91cd72e..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_1.cu deleted file mode 100644 index 4cb791502a..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q8_0.cu deleted file mode 100644 index 09dea42673..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-f16.cu deleted file mode 100644 index 0fbb607694..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_0.cu deleted file mode 100644 index 2aeab83b20..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_1.cu deleted file mode 100644 index 599415b494..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_0.cu deleted file mode 100644 index e4f8e3083b..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_1.cu deleted file mode 100644 index 34d166527e..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q8_0.cu deleted file mode 100644 index 4bebef45a3..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-f16.cu deleted file mode 100644 index 326468da2f..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_0.cu deleted file mode 100644 index 511b58f4ec..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_1.cu deleted file mode 100644 index d9906d142e..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_0.cu deleted file mode 100644 index f61c183abb..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_1.cu deleted file mode 100644 index c10450fd29..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q8_0.cu deleted file mode 100644 index 2d5cb195c4..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-f16.cu deleted file mode 100644 index b384f34d7d..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_0.cu deleted file mode 100644 index 446e293b16..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_1.cu deleted file mode 100644 index 6f43029889..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_0.cu deleted file mode 100644 index 1cd8ba88fd..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_1.cu deleted file mode 100644 index 1ee2eab65a..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q8_0.cu deleted file mode 100644 index 2bc77816a5..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-f16.cu deleted file mode 100644 index d55ced08bc..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_0.cu deleted file mode 100644 index 8361e99c4e..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_1.cu deleted file mode 100644 index 7507a67c4c..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_0.cu deleted file mode 100644 index 61f050b235..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_1.cu deleted file mode 100644 index d4a49d9c99..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q8_0.cu deleted file mode 100644 index d146278976..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs256-f16-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs256-f16-f16.cu deleted file mode 100644 index e73f917a1f..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs256-f16-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(256, GGML_TYPE_F16, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu deleted file mode 100644 index d40825dfc2..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(64, GGML_TYPE_F16, GGML_TYPE_F16); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_0.cu deleted file mode 100644 index b5c6869f4e..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_1.cu deleted file mode 100644 index 4e21b0ccae..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_0.cu deleted file mode 100644 index 2eac321b37..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_1.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_1.cu deleted file mode 100644 index f7d2c3b4e0..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q8_0.cu b/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q8_0.cu deleted file mode 100644 index a013f400bd..0000000000 --- a/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q8_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../fattn-vec-f32.cuh" - -DECL_FATTN_VEC_F32_CASE(64, GGML_TYPE_F16, GGML_TYPE_Q8_0); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq1_s.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-iq1_s.cu deleted file mode 100644 index 84ec850294..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq1_s.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_IQ1_S); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_s.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_s.cu deleted file mode 100644 index 583c4e5a51..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_s.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_IQ2_S); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xs.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xs.cu deleted file mode 100644 index edaf1560de..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xs.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_IQ2_XS); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xxs.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xxs.cu deleted file mode 100644 index 233d9342c9..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xxs.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_IQ2_XXS); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_s.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_s.cu deleted file mode 100644 index 6092dc7136..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_s.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_IQ3_S); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_xxs.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_xxs.cu deleted file mode 100644 index 1d5bd201fb..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_xxs.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_IQ3_XXS); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu deleted file mode 100644 index eb02fab002..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_IQ4_NL); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu deleted file mode 100644 index 1eb3b74307..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_IQ4_XS); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-q2_k.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-q2_k.cu deleted file mode 100644 index 6415369dc1..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-q2_k.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_Q2_K); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-q3_k.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-q3_k.cu deleted file mode 100644 index ffb6213af8..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-q3_k.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_Q3_K); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_0.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_0.cu deleted file mode 100644 index 0c0b0c8a8e..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_Q4_0); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_1.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_1.cu deleted file mode 100644 index ee67f6942a..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_Q4_1); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_0.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_0.cu deleted file mode 100644 index cc57fb9753..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_0.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_Q5_0); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_1.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_1.cu deleted file mode 100644 index 721ac790c4..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_1.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_Q5_1); diff --git a/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_k.cu b/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_k.cu deleted file mode 100644 index a2e90ffd5d..0000000000 --- a/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_k.cu +++ /dev/null @@ -1,5 +0,0 @@ -// This file has been autogenerated by generate_cu_files.py, do not edit manually. - -#include "../mmq.cuh" - -DECL_MMQ_CASE(GGML_TYPE_Q5_K);