| .. |
|
ggml-blas
|
5931c1f233
ggml : add support for dynamic loading of backends (#10469)
|
1 yıl önce |
|
ggml-cann
|
6e1c4cebdb
CANN: Support Opt CONV_TRANSPOSE_1D and ELU (#12786)
|
9 ay önce |
|
ggml-cpu
|
31f7803bc4
ggml-cpu-impl.h: do not redefine bool on POWER9 (#12856)
|
9 ay önce |
|
ggml-cuda
|
7538246e7c
cuda : add f32 to bf16 copy op (#12806)
|
9 ay önce |
|
ggml-hip
|
becade5de7
HIP: implement FlashAttention via rocWMMA for CDNA and RDNA3+ (#12032)
|
10 ay önce |
|
ggml-kompute
|
ba1cb19cdd
llama : add Qwen2VL support + multimodal RoPE (#10361)
|
1 yıl önce |
|
ggml-metal
|
a19b5cef16
llama : fix FA when KV cache is not used (i.e. embeddings) (#12825)
|
9 ay önce |
|
ggml-musa
|
b1b132efcb
cuda : enable CUDA Graph on CUDA Toolkit < 12.x (#12394)
|
10 ay önce |
|
ggml-opencl
|
82974011f3
opencl: better identify Adreno GPU (#12760)
|
9 ay önce |
|
ggml-rpc
|
ab6ab8f809
rpc : send hash when tensor data is above some fixed threshold (#12496)
|
9 ay önce |
|
ggml-sycl
|
656babd6c2
Revert "sycl:remove redundant memcopy in function ggml_backend_sycl_buffer_set_tensor" (#12812)
|
9 ay önce |
|
ggml-vulkan
|
0090950f67
vulkan: In coopmat2 mmq, load q4_k/q5_k scales through shared memory (#12833)
|
9 ay önce |
|
CMakeLists.txt
|
a69f846351
cmake : fix ccache conflict (#12522)
|
9 ay önce |
|
ggml-alloc.c
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
10 ay önce |
|
ggml-backend-impl.h
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
10 ay önce |
|
ggml-backend-reg.cpp
|
ba7654380a
ggml-backend : fix backend search path (#12330)
|
10 ay önce |
|
ggml-backend.cpp
|
5bbe6a9fe9
ggml : portability fixes for VS 2017 (#12150)
|
10 ay önce |
|
ggml-common.h
|
492d7f1ff7
musa: fix all warnings, re-enable `-DLLAMA_FATAL_WARNINGS=ON` in ci and update doc (#12611)
|
9 ay önce |
|
ggml-impl.h
|
2391506ace
ggml-impl.h: fix build on POWER9 (#12855)
|
9 ay önce |
|
ggml-opt.cpp
|
02e4eaf22f
ggml-opt: fix data corruption (ggml/1022)
|
1 yıl önce |
|
ggml-quants.c
|
5bbe6a9fe9
ggml : portability fixes for VS 2017 (#12150)
|
10 ay önce |
|
ggml-quants.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 yıl önce |
|
ggml-threading.cpp
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 yıl önce |
|
ggml-threading.h
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
1 yıl önce |
|
ggml.c
|
e0e912f49b
llama : add option to override model tensor buffers (#11397)
|
9 ay önce |
|
gguf.cpp
|
a6f32f0b34
Fix clang warning in gguf_check_reserved_keys (#12686)
|
9 ay önce |
Piotr Kubaj
31f7803bc4
ggml-cpu-impl.h: do not redefine bool on POWER9 (#12856)