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

cuda : get_row_rounding F32 (#4095)

Browse source 
* Fix #4017

* Update ggml-cuda.cu

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Update ggml-cuda.cu

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

---------

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
This commit is contained in:
Andrew Godfrey 2023-11-17 00:01:15 -08:00 committed by GitHub
parent 4f447a4833
commit b83e149ec6
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
ggml-cuda.cu
View file

@ -6356,6 +6356,7 @@ static int64_t get_row_rounding(ggml_type type) {
case GGML_TYPE_Q8_0:
return max_compute_capability >= CC_RDNA2 ? 128 : 64;
case GGML_TYPE_F16:
case GGML_TYPE_F32:
return 1;
case GGML_TYPE_Q2_K:
return max_compute_capability >= CC_RDNA2 ? 128 : 32;
@ -6378,6 +6379,7 @@ static int64_t get_row_rounding(ggml_type type) {
case GGML_TYPE_Q8_0:
return 64;
case GGML_TYPE_F16:
case GGML_TYPE_F32:
return 1;
case GGML_TYPE_Q2_K:
case GGML_TYPE_Q3_K: