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

metal : initial implementation

Browse source
This commit is contained in:
Georgi Gerganov 2024-01-20 17:32:28 +02:00
parent a9681febd6
commit 1173f49c3b
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
4 changed files with 180 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/test-backend-ops.cpp
View file

@ -1396,6 +1396,10 @@ struct test_flash_attn_ext : public test_case {
return VARS_TO_STR5(typeq, hs, nh, kv, nb);
}
double max_nmse_err() override {
return 5e-4;
}
test_flash_attn_ext(ggml_type typeq = GGML_TYPE_F16,
int64_t hs = 128, int64_t nh = 32, int64_t kv = 96, int64_t nb = 8)
: typeq(typeq), hs(hs), nh(nh), kv(kv), nb(nb) {}