vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Remove Q4_3 which is no better than Q5 (#1218)

Browse source
This commit is contained in:
Stephan Walter 2023-04-28 23:10:43 +00:00 • committed by GitHub
parent 7f15c5c477
commit 36d19a603b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
11 changed files with 21 additions and 359 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml.h
View file

@ -221,7 +221,7 @@ extern "C" {
GGML_TYPE_Q4_0 = 2,
GGML_TYPE_Q4_1 = 3,
GGML_TYPE_Q4_2 = 4,
GGML_TYPE_Q4_3 = 5,
// GGML_TYPE_Q4_3 (5) support has been removed
GGML_TYPE_Q5_0 = 6,
GGML_TYPE_Q5_1 = 7,
GGML_TYPE_Q8_0 = 8,
@ -843,7 +843,6 @@ extern "C" {
GGML_API size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int64_t * hist);
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_q5_0(const float * src, void * dst, int n, int k, int64_t * hist);
GGML_API size_t ggml_quantize_q5_1(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);