alihan/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2023-11-04 02:52:44 +03:00
Code Issues Packages Projects Releases Wiki Activity

whisper : add integer quantization support (#540)

Browse Source 
* whisper : add integer quantization support

* examples : add common-ggml + prepare to add "quantize" tool

* whisper : quantization tool ready

* whisper : fix F32 support

* whisper : try to fix shared lib linkage

* wasm : update quantized models to Q5

* bench.wasm : remove "medium" button

* bench.wasm : fix custom model button

* ggml : add Q5_0 and Q5_1 WASM SIMD

* wasm : add quantized models to all WASM examples

* wasm : bump DB version number to 2

* talk-llama : update example to latest llama.cpp

* node : increase test timeout to 10s

* readme : add information for model quantization

* wasm : add links to other examples
This commit is contained in:
Georgi Gerganov
2023-04-30 18:51:57 +03:00
committed by GitHub
parent 5fd1bdd7fc
commit 794b162a46
41 changed files with 3183 additions and 1010 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
ggml.h
View File

@@ -232,6 +232,20 @@ extern "C" {
GGML_TYPE_COUNT,
};
// model file types
enum ggml_ftype {
GGML_FTYPE_UNKNOWN = -1,
GGML_FTYPE_ALL_F32 = 0,
GGML_FTYPE_MOSTLY_F16 = 1, // except 1d tensors
GGML_FTYPE_MOSTLY_Q4_0 = 2, // except 1d tensors
GGML_FTYPE_MOSTLY_Q4_1 = 3, // except 1d tensors
GGML_FTYPE_MOSTLY_Q4_1_SOME_F16 = 4, // tok_embeddings.weight and output.weight are F16
GGML_FTYPE_MOSTLY_Q4_2 = 5, // except 1d tensors
GGML_FTYPE_MOSTLY_Q8_0 = 7, // except 1d tensors
GGML_FTYPE_MOSTLY_Q5_0 = 8, // except 1d tensors
GGML_FTYPE_MOSTLY_Q5_1 = 9, // except 1d tensors
};
// available tensor operations:
enum ggml_op {
GGML_OP_NONE = 0,
@@ -385,6 +399,8 @@ extern "C" {
GGML_API bool ggml_is_quantized(enum ggml_type type);
GGML_API enum ggml_type ggml_ftype_to_ggml_type(enum ggml_ftype ftype);
// main
GGML_API struct ggml_context * ggml_init(struct ggml_init_params params);