| .. |
|
ggml-blas
|
4d3d455d3c
sync : whisper.cpp (ggml/1359)
|
hai 3 meses |
|
ggml-cann
|
2376b7758c
CANN: Use smart pointers to manage ACL objects (#17238)
|
hai 2 meses |
|
ggml-cpu
|
cb44fc84e8
cmake : fix ARM feature verification (#17170)
|
hai 2 meses |
|
ggml-cuda
|
389ac78b26
ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (#17063)
|
hai 2 meses |
|
ggml-hexagon
|
c273d75375
hexagon: various Op fixes (#17135)
|
hai 2 meses |
|
ggml-hip
|
80d28f104c
HIP: fix AMDGPU_TARGETS, update documentation (#16803)
|
hai 2 meses |
|
ggml-metal
|
7aaeedc098
metal : support I32 -> I32 copy (#17317)
|
hai 2 meses |
|
ggml-musa
|
11f0af5504
CUDA: faster tile FA, add oob checks, more HSs (#16492)
|
hai 3 meses |
|
ggml-opencl
|
52e5d421f1
opencl: fix rms_norm_mul (#17250)
|
hai 2 meses |
|
ggml-rpc
|
41386cf365
rpc : report actual free memory (#16616)
|
hai 3 meses |
|
ggml-sycl
|
72bd7321a7
sycl : unify unary kernels with a generic implementation and enable wide operator support (#17213)
|
hai 2 meses |
|
ggml-vulkan
|
38e2c1b412
vulkan: add log RTE support to fix Nvidia CI (#17320)
|
hai 2 meses |
|
ggml-webgpu
|
647b960bd8
ggml webgpu: faster matrix multiplication/matrix-vector multiplication (#17031)
|
hai 2 meses |
|
ggml-zdnn
|
264f1b5187
zdnn: refactor codebase + add docs (#16178)
|
hai 4 meses |
|
CMakeLists.txt
|
4a5b8aff40
cmake : add version to all shared object files (#17091)
|
hai 2 meses |
|
ggml-alloc.c
|
3470a5c891
ggml-alloc : make gallocr prefer chunks that allow memory reuse (#16788)
|
hai 2 meses |
|
ggml-backend-impl.h
|
898acba681
rpc : add support for multiple devices (#16276)
|
hai 3 meses |
|
ggml-backend-reg.cpp
|
63d2fc46e1
Add experimental ggml-hexagon backend for the Hexagon NPU (#16547)
|
hai 3 meses |
|
ggml-backend.cpp
|
dd091e52f8
sched : fix reserve ignoring user tensor assignments (#17232)
|
hai 2 meses |
|
ggml-common.h
|
fd1234cb46
llama : add gpt-oss (#15091)
|
hai 5 meses |
|
ggml-impl.h
|
389ac78b26
ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (#17063)
|
hai 2 meses |
|
ggml-opt.cpp
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
hai 5 meses |
|
ggml-quants.c
|
f6b4af3d04
ggml : fix uninitialized is_on_grid in quantize_row_iq3_xxs_impl (#15928)
|
hai 4 meses |
|
ggml-quants.h
|
fd1234cb46
llama : add gpt-oss (#15091)
|
hai 5 meses |
|
ggml-threading.cpp
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
hai 1 ano |
|
ggml-threading.h
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
hai 1 ano |
|
ggml.c
|
389ac78b26
ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (#17063)
|
hai 2 meses |
|
ggml.cpp
|
fedf034a98
ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)
|
hai 7 meses |
|
gguf.cpp
|
a81283820a
gguf: gguf_writer refactor (#15691)
|
hai 4 meses |
Ruben Ortlam
38e2c1b412
vulkan: add log RTE support to fix Nvidia CI (#17320)