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

ggml : remove old quantization functions (#5942)

Browse source 
* ggml : remove old quantization functions

ggml-ci

* ggml : simplify ggml_quantize_chunk

ggml-ci

* ggml : restrict correctness

ggml-ci

* ggml : remove hist data from the quantization API

ggml-ci

* tests : remove hist usage in test-backend-ops

ggml-ci

* vulkan : remove hist and fix typo
This commit is contained in:
Georgi Gerganov 2024-03-09 15:53:59 +02:00 • committed by GitHub
parent 97c09585d6
commit 5b09797321
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 131 additions and 568 deletions
Download patch file Download diff file Expand all files Collapse all files

23
ggml.h
View file

@ -2194,25 +2194,18 @@ extern "C" {
GGML_API void ggml_quantize_init(enum ggml_type type);
GGML_API void ggml_quantize_free(void);
// TODO: these would probably get removed in favor of the more general ggml_quantize_chunk
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_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);
GGML_API size_t ggml_quantize_q2_K(const float * src, void * dst, int n, int k, int64_t * hist);
GGML_API size_t ggml_quantize_q3_K(const float * src, void * dst, int n, int k, int64_t * hist);
GGML_API size_t ggml_quantize_q4_K(const float * src, void * dst, int n, int k, int64_t * hist);
GGML_API size_t ggml_quantize_q5_K(const float * src, void * dst, int n, int k, int64_t * hist);
GGML_API size_t ggml_quantize_q6_K(const float * src, void * dst, int n, int k, int64_t * hist);
// some quantization type cannot be used without an importance matrix
GGML_API bool ggml_quantize_requires_imatrix(enum ggml_type type);
// calls ggml_quantize_init internally (i.e. can allocate memory)
GGML_API size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst,
int start, int nrows, int n_per_row, int64_t * hist, const float * imatrix);
GGML_API size_t ggml_quantize_chunk(
enum ggml_type type,
const float * src,
void * dst,
int start,
int nrows,
int n_per_row,
const float * imatrix);
//
// gguf