| .. |
|
ggml-alloc.h
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
vor 10 Monaten |
|
ggml-backend.h
|
360d6533db
ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type (#15797)
|
vor 4 Monaten |
|
ggml-blas.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
vor 1 Jahr |
|
ggml-cann.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
vor 1 Jahr |
|
ggml-cpp.h
|
4254bb4951
ggml : fix ggml_gallocr_ptr type (ggml/1205)
|
vor 8 Monaten |
|
ggml-cpu.h
|
9fcb29f22f
ggml: allow casting between f32 and i32 (#15783)
|
vor 4 Monaten |
|
ggml-cuda.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
vor 1 Jahr |
|
ggml-metal.h
|
0f0a3c2851
metal : make the backend async (#15906)
|
vor 4 Monaten |
|
ggml-opencl.h
|
a76c56fa1a
Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
|
vor 1 Jahr |
|
ggml-opt.h
|
5cdb27e091
finetune: SGD optimizer, more CLI args (#13873)
|
vor 5 Monaten |
|
ggml-rpc.h
|
553a5c3a9f
rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (#12943)
|
vor 8 Monaten |
|
ggml-sycl.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
vor 1 Jahr |
|
ggml-vulkan.h
|
c2a67efe38
vulkan: Make Vulkan optional at runtime (#11493). (#11494)
|
vor 11 Monaten |
|
ggml-webgpu.h
|
21c021745d
ggml: Add initial WebGPU backend (#14521)
|
vor 6 Monaten |
|
ggml-zdnn.h
|
40be51152d
ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorrect zTensor free (#15839)
|
vor 4 Monaten |
|
ggml.h
|
b0d52998b9
cuda : fix supports_op condition for get_rows when number of blocks is too large (#15868)
|
vor 4 Monaten |
|
gguf.h
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
vor 1 Jahr |
Aaron Teo
40be51152d
ggml-zdnn: fix #15414, activate FP16 and BF16 acceleration and incorrect zTensor free (#15839)