| .. |
|
ggml-alloc.h
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
10 mesi fa |
|
ggml-backend.h
|
7f323a589f
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (#13386)
|
8 mesi fa |
|
ggml-blas.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 anno fa |
|
ggml-cann.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 anno fa |
|
ggml-cpp.h
|
4254bb4951
ggml : fix ggml_gallocr_ptr type (ggml/1205)
|
8 mesi fa |
|
ggml-cpu.h
|
77d5e9a76a
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (#13107)
|
8 mesi fa |
|
ggml-cuda.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 anno fa |
|
ggml-kompute.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 anno fa |
|
ggml-metal.h
|
68ff663a04
repo : update links to new url (#11886)
|
11 mesi fa |
|
ggml-opencl.h
|
a76c56fa1a
Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
|
1 anno fa |
|
ggml-opt.h
|
6c35981a64
mnist: fix segmentation fault (ggml/1227)
|
8 mesi fa |
|
ggml-rpc.h
|
553a5c3a9f
rpc : do not wait for response when sending RPC_CMD_SET_TENSOR (#12943)
|
8 mesi fa |
|
ggml-sycl.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 anno fa |
|
ggml-vulkan.h
|
c2a67efe38
vulkan: Make Vulkan optional at runtime (#11493). (#11494)
|
11 mesi fa |
|
ggml.h
|
e16c4731c7
ggml : fix the order of ggml_unary_op (#13718)
|
7 mesi fa |
|
gguf.h
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
1 anno fa |
Xuan-Son Nguyen
e16c4731c7
ggml : fix the order of ggml_unary_op (#13718)