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

ggml : add new Q4_2 quantization (ARM only) (#1046)

Browse source 
* ggml : Q4_2 ARM

* ggml : add ggml_is_quantized()

* llama : update llama_type_name() with Q4_2 entry

* ggml : speed-up q4_2

- 4 threads: ~100ms -> ~90ms
- 8 threads:  ~55ms -> ~50ms

* ggml : optimize q4_2 using vmlaq_n_f32 + vmulq_n_f32
This commit is contained in:
Georgi Gerganov 2023-04-18 23:54:57 +03:00 • committed by GitHub
parent 50a8a2af97
commit 77a73403ca
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 287 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ggml.h
View file

@ -204,7 +204,8 @@ enum ggml_type {
GGML_TYPE_F16 = 1,
GGML_TYPE_Q4_0 = 2,
GGML_TYPE_Q4_1 = 3,
GGML_TYPE_Q8_0 = 4,
GGML_TYPE_Q4_2 = 4,
GGML_TYPE_Q8_0 = 5,
GGML_TYPE_I8,
GGML_TYPE_I16,
GGML_TYPE_I32,
@ -806,6 +807,7 @@ enum ggml_opt_result ggml_opt(
size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int64_t * hist);
size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t * hist);
size_t ggml_quantize_q4_2(const float * src, void * dst, int n, int k, int64_t * hist);
//
// system info