Francis Couture-Harpin bfd2f21fb4 bitnet : replace 1.58b with b1.58, as in the paper

2024-06-28 20:38:12 -04:00

..

ggml-cuda

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-sycl

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

kompute @ 4565194ed7

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

kompute-shaders

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

vulkan-shaders

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

CMakeLists.txt

ggml : add GGML_CUDA_USE_GRAPHS option, restore GGML_CUDA_FORCE_CUBLAS (cmake) (#8140)

2024-06-26 21:34:14 +02:00

ggml-alloc.c

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-backend-impl.h

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-backend.c

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-blas.cpp

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-common.h

bitnet : replace 1.58b with b1.58, as in the paper

2024-06-28 20:38:12 -04:00

ggml-cuda.cu

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-impl.h

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-kompute.cpp

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-metal.m

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-metal.metal

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-quants.c

bitnet : replace 1.58b with b1.58, as in the paper

2024-06-28 20:38:12 -04:00

ggml-quants.h

ggml-quants : 1.625 bpw ternary packing for BitNet 1.58b

2024-06-27 02:06:22 -04:00

ggml-rpc.cpp

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-sycl.cpp

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-vulkan-shaders.hpp

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml-vulkan.cpp

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

ggml.c

ggml-quants : ARM NEON vec_dot for q2_2 and q1_3

2024-06-27 02:06:28 -04:00

sgemm.cpp

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

sgemm.h

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00