| .. |
|
ggml-blas
|
cd6983d56d
ggml : fix field name when new ggml_backend (#14944)
|
5 months ago |
|
ggml-cann
|
a0f98dd604
CANN: Optimize RMS_NORM using cache (#15419)
|
5 months ago |
|
ggml-cpu
|
92f7f0a53c
ggml: add `conv3d` op (#15182)
|
5 months ago |
|
ggml-cuda
|
0a9b43e507
vulkan : support ggml_mean (#15393)
|
5 months ago |
|
ggml-hip
|
29c8fbe4e0
HIP: bump requirement to rocm 6.1 (#15296)
|
5 months ago |
|
ggml-metal
|
945e1f12a6
ggml : fix condition of im2col on Metal backend (#15460)
|
5 months ago |
|
ggml-musa
|
7a6e91ad26
CUDA: replace GGML_CUDA_F16 with CUDA arch checks (#15433)
|
5 months ago |
|
ggml-opencl
|
fb22dd07a6
opencl: mark `argsort` unsupported if cols exceed workgroup limit (#15375)
|
5 months ago |
|
ggml-rpc
|
e71d48e326
ggml-rpc: chunk send()/recv() to avoid EINVAL for very large tensors over RPC (macOS & others) (#15188)
|
5 months ago |
|
ggml-sycl
|
0a9b43e507
vulkan : support ggml_mean (#15393)
|
5 months ago |
|
ggml-vulkan
|
611f419cff
vulkan: optimize rms_norm, and allow the work to spread across multiple SMs (#15281)
|
5 months ago |
|
ggml-webgpu
|
45363632cb
ggml WebGPU: add support for quantization types (#15440)
|
5 months ago |
|
ggml-zdnn
|
ff27f80a74
ggml: initial IBM zDNN backend (#14975)
|
5 months ago |
|
CMakeLists.txt
|
ff27f80a74
ggml: initial IBM zDNN backend (#14975)
|
5 months ago |
|
ggml-alloc.c
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 months ago |
|
ggml-backend-impl.h
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
10 months ago |
|
ggml-backend-reg.cpp
|
ff27f80a74
ggml: initial IBM zDNN backend (#14975)
|
5 months ago |
|
ggml-backend.cpp
|
54a241f505
sched : fix possible use of wrong ids tensor when offloading moe prompt processing (#15488)
|
5 months ago |
|
ggml-common.h
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 months ago |
|
ggml-impl.h
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 months ago |
|
ggml-opt.cpp
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
5 months ago |
|
ggml-quants.c
|
f44f793172
ggml-quants : fix make_qp_quants NANs and IQ1 assertion errors (#15379)
|
5 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
|
92f7f0a53c
ggml: add `conv3d` op (#15182)
|
5 months ago |
|
ggml.cpp
|
fedf034a98
ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)
|
7 months ago |
|
gguf.cpp
|
26a48ad699
ggml : prevent integer overflow in gguf tensor size calculation (#14595)
|
6 months ago |
Jeff Bolz
611f419cff
vulkan: optimize rms_norm, and allow the work to spread across multiple SMs (#15281)