tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-15 23:30:15 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
f8c7caeeb7dd610d9689a8965d1205b23a58d9ae
llama.cpp/ggml
History
Francis Couture-Harpin f8c7caeeb7 cuda : implement ssm scan for Mamba2 
There is still room for improvement, but it works!

* cuda : adapt Mamba1 ssm scan to shape changes from Mamba2
2025-06-19 01:56:04 -04:00
..
cmake
ggml-cpu : rework weak alias on apple targets (#14146)
2025-06-16 13:54:15 +08:00
include
Merge branch 'master' into compilade/mamba2
2025-06-10 19:22:15 -04:00
src
cuda : implement ssm scan for Mamba2
2025-06-19 01:56:04 -04:00
.gitignore
vulkan : cmake integration (#8119)
2024-07-13 18:12:39 +02:00
CMakeLists.txt
ggml : disable warnings for tests when using MSVC (ggml/1273)
2025-06-18 09:59:21 +03:00