| .. |
|
ggml-blas
|
c0b45097c3
rename optimize_graph to graph_optimize (#16082)
|
4 months ago |
|
ggml-cann
|
c0b45097c3
rename optimize_graph to graph_optimize (#16082)
|
4 months ago |
|
ggml-cpu
|
624207e676
devops: add s390x & ppc64le CI (#15925)
|
4 months ago |
|
ggml-cuda
|
c0bfc57af4
CUDA: mul_mat_id for mmf for bs <= 64 for f16 and bs <= 32 for f32 (#16277)
|
4 months ago |
|
ggml-hip
|
29c8fbe4e0
HIP: bump requirement to rocm 6.1 (#15296)
|
5 months ago |
|
ggml-metal
|
54dbc37053
metal : report OOM errors (#16274)
|
4 months ago |
|
ggml-musa
|
7a6e91ad26
CUDA: replace GGML_CUDA_F16 with CUDA arch checks (#15433)
|
5 months ago |
|
ggml-opencl
|
3ecb2f671a
ggml : implement set_rows with i32 index (#16159)
|
4 months ago |
|
ggml-rpc
|
c498fc82fe
rpc : use ggml logging facilities
|
4 months ago |
|
ggml-sycl
|
3ecb2f671a
ggml : implement set_rows with i32 index (#16159)
|
4 months ago |
|
ggml-vulkan
|
0499b29c6f
vulkan: throw system error instead of SIGABRT during init on older devices (#16156)
|
4 months ago |
|
ggml-webgpu
|
3ecb2f671a
ggml : implement set_rows with i32 index (#16159)
|
4 months ago |
|
ggml-zdnn
|
264f1b5187
zdnn: refactor codebase + add docs (#16178)
|
4 months ago |
|
CMakeLists.txt
|
246c0d9c79
cmake : fix static linking for OpenMP on Unix-like systems (#16031)
|
4 months ago |
|
ggml-alloc.c
|
f2a789e334
ggml : split graph allocations according to backend max buffer size (#15815)
|
4 months ago |
|
ggml-backend-impl.h
|
c0b45097c3
rename optimize_graph to graph_optimize (#16082)
|
4 months ago |
|
ggml-backend-reg.cpp
|
360d6533db
ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type (#15797)
|
4 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
|
f2a789e334
ggml : split graph allocations according to backend max buffer size (#15815)
|
4 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
|
624207e676
devops: add s390x & ppc64le CI (#15925)
|
4 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 |
Aman Gupta
c0bfc57af4
CUDA: mul_mat_id for mmf for bs <= 64 for f16 and bs <= 32 for f32 (#16277)