diff options
Diffstat (limited to 'ggml/src/iqk/iqk_mul_mat.cpp')
| -rw-r--r-- | ggml/src/iqk/iqk_mul_mat.cpp | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/ggml/src/iqk/iqk_mul_mat.cpp b/ggml/src/iqk/iqk_mul_mat.cpp index 6925e6a6..f718e43e 100644 --- a/ggml/src/iqk/iqk_mul_mat.cpp +++ b/ggml/src/iqk/iqk_mul_mat.cpp @@ -236,9 +236,6 @@ struct MulMat { static inline ggml_type is_dequant_better(ggml_type type, int nrc_y) { #ifdef __AVX2__ switch (type) { - case GGML_TYPE_IQ2_KT : return nrc_y >= 32 ? GGML_TYPE_F32 : type; - case GGML_TYPE_IQ3_KT : return nrc_y >= 32 ? GGML_TYPE_F32 : type; - case GGML_TYPE_IQ4_KT : return nrc_y >= 32 ? GGML_TYPE_F32 : type; case GGML_TYPE_IQ2_XXS: return nrc_y >= 32 ? GGML_TYPE_Q8_K_R8 : type; case GGML_TYPE_IQ2_XS : return nrc_y >= 32 ? GGML_TYPE_Q8_K_R8 : type; case GGML_TYPE_IQ2_S : return nrc_y >= 16 ? GGML_TYPE_Q8_K_R8 : type; @@ -267,13 +264,16 @@ struct MulMat { case GGML_TYPE_Q6_0 : return nrc_y >= 32 ? GGML_TYPE_Q8_0_R8 : type; case GGML_TYPE_IQ4_NL : return nrc_y >= 32 ? GGML_TYPE_Q8_0_R8 : type; case GGML_TYPE_Q8_0 : return nrc_y >= 32 ? GGML_TYPE_Q8_0_R8 : type; + case GGML_TYPE_IQ2_KT : return nrc_y >= 32 ? GGML_TYPE_Q8_0_R8 : type; + case GGML_TYPE_IQ3_KT : return nrc_y >= 32 ? GGML_TYPE_Q8_0_R8 : type; + case GGML_TYPE_IQ4_KT : return nrc_y >= 32 ? GGML_TYPE_Q8_0_R8 : type; default: break; } #else switch (type) { - case GGML_TYPE_IQ2_KT: return nrc_y >= 32 ? GGML_TYPE_F16 : type; + case GGML_TYPE_IQ2_KT: return nrc_y >= 32 ? GGML_TYPE_Q8_0_R8 : type; case GGML_TYPE_IQ3_KT: return nrc_y >= 32 ? GGML_TYPE_F16 : type; - case GGML_TYPE_IQ4_KT: return nrc_y >= 32 ? GGML_TYPE_F16 : type; + case GGML_TYPE_IQ4_KT: return nrc_y >= 32 ? GGML_TYPE_Q8_0_R8 : type; default: break; } #endif @@ -815,7 +815,7 @@ bool MulMat::prepare(int typeA, int typeB, int ne00, MulMat& mm, int Ny) { case GGML_TYPE_IQ2_KT: case GGML_TYPE_IQ3_KT: case GGML_TYPE_IQ4_KT: - return ggml_type(typeB) == GGML_TYPE_F32 ? iqk_set_kernels_ktquants(ne00, typeA, typeB, mm.funcs, mm.func16) : false; + return iqk_set_kernels_ktquants(ne00, typeA, typeB, mm.funcs, mm.func16); case GGML_TYPE_Q4_0: case GGML_TYPE_Q4_1: case GGML_TYPE_Q5_0: |