aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorGeorgi Gerganov <ggerganov@gmail.com>2023-04-20 20:44:05 +0300
committerGeorgi Gerganov <ggerganov@gmail.com>2023-04-20 20:44:05 +0300
commit66aab46079609972ee1f7bd6f319d826205a2fbd (patch)
tree688881ec6a128f4be1cdf99ac907555fd10dd069
parent38de86a7114c97ecf3644e3a60159f1ed893e1b0 (diff)
ggml : fix Q4_3 quantization
Broke it during conflict resolution in last PR
-rw-r--r--ggml.c6
1 files changed, 6 insertions, 0 deletions
diff --git a/ggml.c b/ggml.c
index 1aa8ee3..50f114d 100644
--- a/ggml.c
+++ b/ggml.c
@@ -12210,6 +12210,12 @@ size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, i
block_q4_2 * block = (block_q4_2*)dst + start / QK4_2;
result = ggml_quantize_q4_2(src + start, block, n, n, hist);
} break;
+ case GGML_TYPE_Q4_3:
+ {
+ GGML_ASSERT(start % QK4_3 == 0);
+ block_q4_3 * block = (block_q4_3*)dst + start / QK4_3;
+ result = ggml_quantize_q4_3(src + start, block, n, n, hist);
+ } break;
default:
assert(false);
}