tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 04:15:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : add BF16 support (#8439)

Browse Source 
* ggml : add initial BF16 support

ggml-ci

* metal : add mul_mat_id BF16 support

ggml-ci

* metal : check for bfloat support on the Metal device

ggml-ci

* metal : better var names [no ci]

* metal : do not build bfloat kernels when not supported

ggml-ci

* metal : try to fix BF16 support check

ggml-ci

* metal : this should correctly check bfloat support
This commit is contained in:
Georgi Gerganov
2024-11-06 19:53:51 +02:00
committed by GitHub
parent b11f9ba9b8
commit 5c333e0140
4 changed files with 317 additions and 184 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
common/common.cpp
View File

@ -1003,6 +1003,9 @@ static ggml_type kv_cache_type_from_str(const std::string & s) {
if (s == "f16") {
return GGML_TYPE_F16;
}
if (s == "bf16") {
return GGML_TYPE_BF16;
}
if (s == "q8_0") {
return GGML_TYPE_Q8_0;
}