ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

CUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (#13137)

Browse source
This commit is contained in:
Johannes Gäßler 2025-04-28 09:29:26 +02:00 • committed by GitHub
parent 85f36e5e71
commit 69699be48a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 5 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ggml/include/ggml.h
View file

@ -393,8 +393,8 @@ extern "C" {
// precision
enum ggml_prec {
GGML_PREC_DEFAULT,
GGML_PREC_F32,
GGML_PREC_DEFAULT = 0, // stored as ggml_tensor.op_params, 0 by default
GGML_PREC_F32 = 10,
};
// model file types