tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-19 22:36:13 -04:00
Code Issues Packages Projects Releases Wiki Activity

ggml : add Q8_0 quantization format (rename the old one to Q8_1) (ARM NEON) (#1179)

Browse Source 
* ggml : add Q8_0 quantization format (rename the old one to Q8_1)

* tests : fix test-quantize-fns

* ggml : finalize Q8_0 implementation

* ggml : use q4_0_q8_0 and q4_2_q8_0

* ggml : fix Q8_0 dot product bug (ARM)

* ggml : Q8_0 unroll x2

* ggml : fix bug - using wrong block type

* ggml : extend quantize_fns_t with "vec_dot_type"

* ggml : fix Q8_0 to use 255 values out of 256

* ggml : fix assert using wrong QK4_2 instead of QK4_3
This commit is contained in:
Georgi Gerganov
2023-04-25 23:40:51 +03:00
committed by GitHub
parent dd0eabc049
commit 7a32fcb3b2
8 changed files with 312 additions and 147 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml.h
View File

@@ -223,6 +223,7 @@ extern "C" {
GGML_TYPE_Q4_2 = 4,
GGML_TYPE_Q4_3 = 5,
GGML_TYPE_Q8_0 = 6,
GGML_TYPE_Q8_1 = 7,
GGML_TYPE_I8,
GGML_TYPE_I16,
GGML_TYPE_I32,
@@ -832,6 +833,7 @@ extern "C" {
GGML_API size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t * hist);
GGML_API size_t ggml_quantize_q4_2(const float * src, void * dst, int n, int k, int64_t * hist);
GGML_API size_t ggml_quantize_q4_3(const float * src, void * dst, int n, int k, int64_t * hist);
GGML_API size_t ggml_quantize_q8_0(const float * src, void * dst, int n, int k, int64_t * hist);
GGML_API size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, int start, int n, int64_t * hist);
@@ -876,6 +878,7 @@ extern "C" {
quantize_row_q_t quantize_row_q_reference;
quantize_row_q_t quantize_row_q_dot;
vec_dot_q_t vec_dot_q;
enum ggml_type vec_dot_type;
} quantize_fns_t;
quantize_fns_t ggml_internal_get_quantize_fn(size_t i);