root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-15 07:19:53 +00:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity
3bc7103d2e
llama.cpp/ggml
History
Francis Couture-Harpin 3bc7103d2e ggml : avoid multiply by D in GGML_OP_SSM_SCAN 
This makes the weight buft detection in src/llama.cpp simpler.

* convert : transpose Mamba-2 A, D and reshape SSM_NORM

This breaks existing conversions of Mamba-2 models
to avoid some reshapes.

Not sure if it's a good idea,
but it makes the graph slightly cleaner.

* llama : more appropriate SSM_SCAN and SSM_CONV buft support checks
2024-11-04 13:29:47 -05:00
..
cmake llama : reorganize source code + improve CMake (#8006) 2024-06-26 18:33:02 +03:00
include ggml : avoid multiply by D in GGML_OP_SSM_SCAN 2024-11-04 13:29:47 -05:00
src ggml : avoid multiply by D in GGML_OP_SSM_SCAN 2024-11-04 13:29:47 -05:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt add amx kernel for gemm (#8998) 2024-10-18 13:34:36 +08:00