summaryrefslogtreecommitdiff
path: root/ggml/src/ggml-quants.c
diff options
context:
space:
mode:
authorKawrakow <iwankawrakow@gmail.com>2024-12-02 17:01:48 +0100
committerGitHub <noreply@github.com>2024-12-02 17:01:48 +0100
commit239a344f9935cb614c6208000edb0815214286a1 (patch)
treeaaa1933857cd9575fecfec14515e43e24305ce1f /ggml/src/ggml-quants.c
parent6d0462d4a39085a9f9da04e0a5fc7cc9d4578818 (diff)
Q4_0_R4 (#119)
* Adding iq4_0_r4 - q4_0 repacked We get PP-512(LLaMA-3.1-8B) = 278 t/s on a Ryzen-7950X CPU, so ~5-6% faster than iq4_nl_x4. * q4_0_r4: NEON Here we get 115.8 t/s, so also ~5% better than iq4_nl_x4. --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml/src/ggml-quants.c')
-rw-r--r--ggml/src/ggml-quants.c1
1 files changed, 1 insertions, 0 deletions
diff --git a/ggml/src/ggml-quants.c b/ggml/src/ggml-quants.c
index 376c97f8..dd43e1c1 100644
--- a/ggml/src/ggml-quants.c
+++ b/ggml/src/ggml-quants.c
@@ -15197,6 +15197,7 @@ bool ggml_validate_row_data(enum ggml_type type, const void * data, size_t nbyte
case GGML_TYPE_IQ4_KS: break;
case GGML_TYPE_IQ4_KSS: break;
case GGML_TYPE_IQ4_NL_X4: break;
+ case GGML_TYPE_Q4_0_R4: break;
case GGML_TYPE_Q4_0_4_4:
case GGML_TYPE_Q4_0_4_8:
{