| .. |
|
ggml-blas
|
4d3d455d3c
sync : whisper.cpp (ggml/1359)
|
3 ماه پیش |
|
ggml-cann
|
dcb7d17758
cann : fix ops broken by circular padding guard (#17825)
|
1 ماه پیش |
|
ggml-cpu
|
51604435e8
ggml-cpu : fix RISC-V Q4_0 repack select and RVV feature reporting (#17951)
|
1 ماه پیش |
|
ggml-cuda
|
482211438d
CUDA: fix overflow in MMA kernel without stream-k (#17939)
|
1 ماه پیش |
|
ggml-hexagon
|
34ce48d97a
ggml-hexagon: fix `rope` failure at `test-backend-ops` (#17565)
|
1 ماه پیش |
|
ggml-hip
|
80d28f104c
HIP: fix AMDGPU_TARGETS, update documentation (#16803)
|
2 ماه پیش |
|
ggml-metal
|
086a63e3a5
metal: SSM kernel improvements (#17876)
|
1 ماه پیش |
|
ggml-musa
|
11f0af5504
CUDA: faster tile FA, add oob checks, more HSs (#16492)
|
3 ماه پیش |
|
ggml-opencl
|
09c7c50e64
ggml : add circular tiling support to pad, for Vulkan, CUDA, and CPU (used for making seamless textures) (#16985)
|
1 ماه پیش |
|
ggml-rpc
|
7b43f55753
ggml : improve error handling for search path existence checks (#17653)
|
1 ماه پیش |
|
ggml-sycl
|
2e9eab80c2
fix softmax for iGPU (#17838)
|
1 ماه پیش |
|
ggml-vulkan
|
07a10c1090
vulkan: Allow non-pow2 n_experts in topk_moe (#17872)
|
1 ماه پیش |
|
ggml-webgpu
|
fd57b24c0f
ggml webgpu: unary op suppport, code refactoring, ops support (#17764)
|
1 ماه پیش |
|
ggml-zdnn
|
264f1b5187
zdnn: refactor codebase + add docs (#16178)
|
4 ماه پیش |
|
ggml-zendnn
|
017761daf5
ggml-zendnn : add ZenDNN backend for AMD CPUs (#17690)
|
1 ماه پیش |
|
CMakeLists.txt
|
017761daf5
ggml-zendnn : add ZenDNN backend for AMD CPUs (#17690)
|
1 ماه پیش |
|
ggml-alloc.c
|
c6f6e4f96a
ggml-alloc : fix reuse-parent logic for misaligned sizes (#17884)
|
1 ماه پیش |
|
ggml-backend-impl.h
|
898acba681
rpc : add support for multiple devices (#16276)
|
3 ماه پیش |
|
ggml-backend-reg.cpp
|
017761daf5
ggml-zendnn : add ZenDNN backend for AMD CPUs (#17690)
|
1 ماه پیش |
|
ggml-backend.cpp
|
7f3a72a8ed
ggml : remove redundant n_copies check when setting input/output (#17612)
|
1 ماه پیش |
|
ggml-common.h
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 ماه پیش |
|
ggml-impl.h
|
389ac78b26
ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (#17063)
|
2 ماه پیش |
|
ggml-opt.cpp
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
5 ماه پیش |
|
ggml-quants.c
|
f6b4af3d04
ggml : fix uninitialized is_on_grid in quantize_row_iq3_xxs_impl (#15928)
|
4 ماه پیش |
|
ggml-quants.h
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 ماه پیش |
|
ggml-threading.cpp
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 سال پیش |
|
ggml-threading.h
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
1 سال پیش |
|
ggml.c
|
4dff236a52
ggml : remove GGML_KQ_MASK_PAD constant (#17910)
|
1 ماه پیش |
|
ggml.cpp
|
fedf034a98
ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)
|
7 ماه پیش |
|
gguf.cpp
|
37adc9c6ba
ggml, llama : use defaulted constructors/destructors (#17649)
|
1 ماه پیش |
Jeff Bolz
07a10c1090
vulkan: Allow non-pow2 n_experts in topk_moe (#17872)