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

metal : support Q > 8

Browse source
This commit is contained in:
Georgi Gerganov 2024-01-28 23:08:31 +02:00
parent 134c81c78d
commit 1db22d7032
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
3 changed files with 55 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/batched-bench/batched-bench.cpp
View file

@ -104,7 +104,7 @@ int main(int argc, char ** argv) {
ctx_params.seed = 1234;
ctx_params.n_ctx = n_kv_max;
ctx_params.n_batch = 512;
ctx_params.n_batch = 2048;
ctx_params.mul_mat_q = mmq;
ctx_params.n_threads = params.n_threads;