| .. |
|
ggml-blas
|
4d3d455d3c
sync : whisper.cpp (ggml/1359)
|
3 months ago |
|
ggml-cann
|
7a50cf388a
CANN: format code using .clang-format (#15863)
|
3 months ago |
|
ggml-cpu
|
4f73d0a951
ci : fix binaries release failure for s390x (binaries may not work yet) (#16664)
|
3 months ago |
|
ggml-cuda
|
38355c6c8e
CUDA: use registers instead of smem in topk-moe (#16647)
|
3 months ago |
|
ggml-hip
|
ee09828cb0
HIP: fix GPU_TARGETS (#16642)
|
3 months ago |
|
ggml-metal
|
9ad4f1931e
metal : add `CONV_TRANSPOSE_2D` (#16542)
|
3 months ago |
|
ggml-musa
|
11f0af5504
CUDA: faster tile FA, add oob checks, more HSs (#16492)
|
3 months ago |
|
ggml-opencl
|
81387858f1
opencl: transposed gemm/gemv moe kernel with mxfp4,f32 (#16602)
|
3 months ago |
|
ggml-rpc
|
41386cf365
rpc : report actual free memory (#16616)
|
3 months ago |
|
ggml-sycl
|
2330de7b84
SYCL: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators (#16613)
|
3 months ago |
|
ggml-vulkan
|
e56abd2098
vulkan: Implement topk_moe fused shader, ported from CUDA (#16641)
|
3 months ago |
|
ggml-webgpu
|
74b8fc17f9
ggml webgpu: profiling, CI updates, reworking of command submission (#16452)
|
3 months ago |
|
ggml-zdnn
|
264f1b5187
zdnn: refactor codebase + add docs (#16178)
|
4 months ago |
|
CMakeLists.txt
|
4f73d0a951
ci : fix binaries release failure for s390x (binaries may not work yet) (#16664)
|
3 months ago |
|
ggml-alloc.c
|
b617cfd289
ggml-alloc : fix leak when reusing a tensor with a larger size (#16679)
|
3 months ago |
|
ggml-backend-impl.h
|
898acba681
rpc : add support for multiple devices (#16276)
|
3 months ago |
|
ggml-backend-reg.cpp
|
02463ab27b
ggml-backend : add root cause in error message if loading backend library fails (#16172)
|
3 months ago |
|
ggml-backend.cpp
|
e789095502
llama: print memory breakdown on exit (#15860)
|
4 months ago |
|
ggml-common.h
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 months ago |
|
ggml-impl.h
|
e56abd2098
vulkan: Implement topk_moe fused shader, ported from CUDA (#16641)
|
3 months ago |
|
ggml-opt.cpp
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
5 months ago |
|
ggml-quants.c
|
f6b4af3d04
ggml : fix uninitialized is_on_grid in quantize_row_iq3_xxs_impl (#15928)
|
4 months ago |
|
ggml-quants.h
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 months ago |
|
ggml-threading.cpp
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
ggml-threading.h
|
cb13ef85a4
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
|
1 year ago |
|
ggml.c
|
466c1911ab
cpu : add FLOOR, CEIL, ROUND and TRUNC unary operators (#16083)
|
3 months ago |
|
ggml.cpp
|
fedf034a98
ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)
|
7 months ago |
|
gguf.cpp
|
a81283820a
gguf: gguf_writer refactor (#15691)
|
4 months ago |
Diego Devesa
b617cfd289
ggml-alloc : fix leak when reusing a tensor with a larger size (#16679)