vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
llama.cpp/ggml/include
History
Johannes Gäßler e11bd856d5
CPU/CUDA: Gemma 2 FlashAttention support (#8542) 
* CPU/CUDA: Gemma 2 FlashAttention support

* apply logit_softcap to scale in kernel

* disable logit softcapping tests on Metal

* remove metal check
2024-08-24 21:34:59 +02:00
..
ggml-alloc.h llama : reorganize source code + improve CMake (#8006) 2024-06-26 18:33:02 +03:00
ggml-backend.h CUDA: fix partial offloading for ne0 % 256 != 0 (#8572) 2024-07-18 23:48:47 +02:00
ggml-blas.h llama : reorganize source code + improve CMake (#8006) 2024-06-26 18:33:02 +03:00
ggml-cann.h [CANN] Add Ascend NPU backend (#6035) 2024-07-17 14:23:50 +03:00
ggml-cuda.h feat: Support Moore Threads GPU (#8383) 2024-07-28 01:41:25 +02:00
ggml-kompute.h llama : reorganize source code + improve CMake (#8006) 2024-06-26 18:33:02 +03:00
ggml-metal.h metal : add abort callback (ggml/905) 2024-08-08 13:19:30 +03:00
ggml-rpc.h llama : reorganize source code + improve CMake (#8006) 2024-06-26 18:33:02 +03:00
ggml-sycl.h llama : reorganize source code + improve CMake (#8006) 2024-06-26 18:33:02 +03:00
ggml-vulkan.h llama : reorganize source code + improve CMake (#8006) 2024-06-26 18:33:02 +03:00
ggml.h CPU/CUDA: Gemma 2 FlashAttention support (#8542) 2024-08-24 21:34:59 +02:00