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

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
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 312 additions and 147 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/quantize/quantize.cpp
View file

@ -16,6 +16,7 @@ int main(int argc, char ** argv) {
fprintf(stderr, " type = %d - q4_1\n", LLAMA_FTYPE_MOSTLY_Q4_1);
fprintf(stderr, " type = %d - q4_2\n", LLAMA_FTYPE_MOSTLY_Q4_2);
fprintf(stderr, " type = %d - q4_3\n", LLAMA_FTYPE_MOSTLY_Q4_3);
fprintf(stderr, " type = %d - q8_0\n", LLAMA_FTYPE_MOSTLY_Q8_0);
return 1;
}