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

metal : pad n_ctx by 32 (#6177)

Browse source 
* metal : require ne00 >= 128 for mat-mat kernels

ggml-ci

* llama : pad n_ctx by 32

ggml-ci
This commit is contained in:
Georgi Gerganov 2024-03-22 09:36:03 +02:00 • committed by GitHub
parent 59c17f02de
commit 95d576b48e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 14 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.cpp
View file

@ -101,7 +101,7 @@ int32_t get_num_physical_cores() {
return n_threads > 0 ? (n_threads <= 4 ? n_threads : n_threads / 2) : 4;
}
void process_escapes(std::string& input) {
void process_escapes(std::string & input) {
std::size_t input_len = input.length();
std::size_t output_idx = 0;