diff options
Diffstat (limited to 'ggml/src/ggml.c')
| -rw-r--r-- | ggml/src/ggml.c | 29 |
1 files changed, 28 insertions, 1 deletions
diff --git a/ggml/src/ggml.c b/ggml/src/ggml.c index 7ad666eb..97fa81b1 100644 --- a/ggml/src/ggml.c +++ b/ggml/src/ggml.c @@ -1087,6 +1087,19 @@ static const ggml_type_traits_t type_traits[GGML_TYPE_COUNT] = { .nrows = 1, .row_meta_size = 0, }, + [GGML_TYPE_IQ4_KS] = { + .type_name = "iq4_ks", + .blck_size = QK_K, + .type_size = sizeof(block_iq4_ks), + .is_quantized = true, + .to_float = (ggml_to_float_t) dequantize_row_iq4_ks, + .from_float = quantize_row_iq4_ks, + .from_float_ref = (ggml_from_float_t)quantize_row_iq4_ks_ref, + .vec_dot = vec_dot_iq4_ks_q8_k, + .vec_dot_type = GGML_TYPE_Q8_K, + .nrows = 1, + .row_meta_size = 4, + }, [GGML_TYPE_Q8_K] = { .type_name = "q8_K", .blck_size = QK_K, @@ -3891,6 +3904,7 @@ enum ggml_type ggml_ftype_to_ggml_type(enum ggml_ftype ftype) { case GGML_FTYPE_MOSTLY_IQ1_TN: wtype = GGML_TYPE_IQ1_TN; break; case GGML_FTYPE_MOSTLY_IQ4_NL: wtype = GGML_TYPE_IQ4_NL; break; case GGML_FTYPE_MOSTLY_IQ4_XS: wtype = GGML_TYPE_IQ4_XS; break; + case GGML_FTYPE_MOSTLY_IQ4_KS: wtype = GGML_TYPE_IQ4_KS; break; case GGML_FTYPE_MOSTLY_IQ2_K: wtype = GGML_TYPE_IQ2_K; break; case GGML_FTYPE_MOSTLY_IQ3_K: wtype = GGML_TYPE_IQ3_K; break; case GGML_FTYPE_MOSTLY_IQ4_K: wtype = GGML_TYPE_IQ4_K; break; @@ -10390,6 +10404,7 @@ static void ggml_compute_forward_add( case GGML_TYPE_IQ1_TN: case GGML_TYPE_IQ4_NL: case GGML_TYPE_IQ4_XS: + case GGML_TYPE_IQ4_KS: case GGML_TYPE_IQ2_K: case GGML_TYPE_IQ3_K: case GGML_TYPE_IQ4_K: @@ -10778,6 +10793,7 @@ static void ggml_compute_forward_add1( case GGML_TYPE_IQ1_TN: case GGML_TYPE_IQ4_NL: case GGML_TYPE_IQ4_XS: + case GGML_TYPE_IQ4_KS: case GGML_TYPE_IQ2_K: case GGML_TYPE_IQ3_K: case GGML_TYPE_IQ4_K: @@ -10916,6 +10932,7 @@ static void ggml_compute_forward_acc( case GGML_TYPE_IQ1_TN: case GGML_TYPE_IQ4_NL: case GGML_TYPE_IQ4_XS: + case GGML_TYPE_IQ4_KS: case GGML_TYPE_IQ2_K: case GGML_TYPE_IQ3_K: case GGML_TYPE_IQ4_K: @@ -13262,7 +13279,7 @@ static void ggml_compute_forward_mul_mat_one_chunk( return; } - const void * wdata = (src1->type == vec_dot_type) ? src1->data : params->wdata; + const void * wdata = (src1->type == vec_dot_type) ? src1->data : (char *)params->wdata + params->wsize - params->qsize + GGML_MAX_NAME; const size_t row_size = ggml_row_size(vec_dot_type, ne10); assert(ne12 % ne02 == 0); @@ -13517,6 +13534,11 @@ IQK_MulMat_Not_Available2:; UseGgmlGemm2:; #endif + if (ith == 0) { + atomic_store(¶ms->shared->current_chunk, nth); + } + ggml_barrier(params->shared); + // This is the size of the first dimension of the result, so we can iterate that way. (see the ASSERT above, these are the same numbers) const int64_t nr0 = ne0; @@ -14095,6 +14117,7 @@ static void ggml_compute_forward_out_prod( case GGML_TYPE_IQ1_TN: case GGML_TYPE_IQ4_NL: case GGML_TYPE_IQ4_XS: + case GGML_TYPE_IQ4_KS: case GGML_TYPE_IQ2_K: case GGML_TYPE_IQ3_K: case GGML_TYPE_IQ4_K: @@ -14473,6 +14496,7 @@ static void ggml_compute_forward_set( case GGML_TYPE_IQ1_TN: case GGML_TYPE_IQ4_NL: case GGML_TYPE_IQ4_XS: + case GGML_TYPE_IQ4_KS: case GGML_TYPE_IQ2_K: case GGML_TYPE_IQ3_K: case GGML_TYPE_IQ4_K: @@ -14745,6 +14769,7 @@ static void ggml_compute_forward_get_rows( case GGML_TYPE_IQ1_TN: case GGML_TYPE_IQ4_NL: case GGML_TYPE_IQ4_XS: + case GGML_TYPE_IQ4_KS: case GGML_TYPE_IQ2_K: case GGML_TYPE_IQ3_K: case GGML_TYPE_IQ4_K: @@ -15344,6 +15369,7 @@ static void ggml_compute_forward_clamp( case GGML_TYPE_IQ1_TN: case GGML_TYPE_IQ4_NL: case GGML_TYPE_IQ4_XS: + case GGML_TYPE_IQ4_KS: case GGML_TYPE_IQ2_K: case GGML_TYPE_IQ3_K: case GGML_TYPE_IQ4_K: @@ -22160,6 +22186,7 @@ size_t ggml_quantize_chunk( case GGML_TYPE_IQ1_TN: result = quantize_iq1_tn (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; case GGML_TYPE_IQ4_NL: result = quantize_iq4_nl (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; case GGML_TYPE_IQ4_XS: result = quantize_iq4_xs (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; + case GGML_TYPE_IQ4_KS: result = quantize_iq4_ks (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; case GGML_TYPE_IQ2_K: result = quantize_iq2_k (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; case GGML_TYPE_IQ3_K: result = quantize_iq3_k (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; case GGML_TYPE_IQ4_K: result = quantize_iq4_k (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break; |