root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-11 21:39:52 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

ggml : fix Q4_3 quantization

Browse Source 
Broke it during conflict resolution in last PR
This commit is contained in:
Georgi Gerganov 2023-04-20 20:44:05 +03:00
parent 38de86a711
commit 66aab46079
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
ggml.c
View File

@ -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; block_q4_2 * block = (block_q4_2*)dst + start / QK4_2;
result = ggml_quantize_q4_2(src + start, block, n, n, hist); result = ggml_quantize_q4_2(src + start, block, n, n, hist);
} break; } 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: default:
assert(false); assert(false);
} }