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

llama : initial Mamba-2 support

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-08-01 10:43:42 -04:00
parent a1631e53f6
commit 1f0fea70fb
7 changed files with 490 additions and 82 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml/include/ggml.h
View file

@ -1787,7 +1787,8 @@ extern "C" {
struct ggml_tensor * dt,
struct ggml_tensor * A,
struct ggml_tensor * B,
struct ggml_tensor * C);
struct ggml_tensor * C,
struct ggml_tensor * D);
// partition into non-overlapping windows with padding if needed
// example: