CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : avoid redundant state copy for Mamba 1 and 2

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-09-30 15:52:42 -04:00
parent 0e601cafe9
commit 273e7a495a
4 changed files with 142 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/include/ggml.h
View File

@@ -1833,7 +1833,8 @@ extern "C" {
struct ggml_tensor * A,
struct ggml_tensor * B,
struct ggml_tensor * C,
struct ggml_tensor * D);
struct ggml_tensor * D,
struct ggml_tensor * ids);
// partition into non-overlapping windows with padding if needed
// example: