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

metal : use F16 precision in FA kernels

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-11-06 15:33:30 +02:00
parent 25e877309a
commit 7facc29d69
No known key found for this signature in database
GPG key ID: BF970631944C16B7
7 changed files with 476 additions and 333 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/llama-bench/llama-bench.cpp
View file

@ -256,6 +256,9 @@ static ggml_type ggml_type_from_name(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;
}