| .. |
|
ggml-alloc.h
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
hai 10 meses |
|
ggml-backend.h
|
898acba681
rpc : add support for multiple devices (#16276)
|
hai 3 meses |
|
ggml-blas.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
hai 1 ano |
|
ggml-cann.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
hai 1 ano |
|
ggml-cpp.h
|
4254bb4951
ggml : fix ggml_gallocr_ptr type (ggml/1205)
|
hai 8 meses |
|
ggml-cpu.h
|
9fcb29f22f
ggml: allow casting between f32 and i32 (#15783)
|
hai 4 meses |
|
ggml-cuda.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
hai 1 ano |
|
ggml-hexagon.h
|
63d2fc46e1
Add experimental ggml-hexagon backend for the Hexagon NPU (#16547)
|
hai 2 meses |
|
ggml-metal.h
|
0320ac5264
metal : refactor + optimize v2 (#15995)
|
hai 4 meses |
|
ggml-opencl.h
|
a76c56fa1a
Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
|
hai 1 ano |
|
ggml-opt.h
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
hai 5 meses |
|
ggml-rpc.h
|
41386cf365
rpc : report actual free memory (#16616)
|
hai 3 meses |
|
ggml-sycl.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
hai 1 ano |
|
ggml-vulkan.h
|
c2a67efe38
vulkan: Make Vulkan optional at runtime (#11493). (#11494)
|
hai 11 meses |
|
ggml-webgpu.h
|
21c021745d
ggml: Add initial WebGPU backend (#14521)
|
hai 6 meses |
|
ggml-zdnn.h
|
264f1b5187
zdnn: refactor codebase + add docs (#16178)
|
hai 3 meses |
|
ggml.h
|
389ac78b26
ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (#17063)
|
hai 2 meses |
|
gguf.h
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
hai 1 ano |
Piotr Wilkin (ilintar)
389ac78b26
ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (#17063)