| .. |
|
hexagon
|
ce734a8a2f
ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977)
|
há 4 semanas atrás |
|
BLIS.md
|
8648c52101
make : deprecate (#10514)
|
há 1 ano atrás |
|
CANN.md
|
23a46ce972
CANN: GGML_CANN_ACL_GRAPH works only USE_ACL_GRAPH enabled (#16861)
|
há 2 meses atrás |
|
CUDA-FEDORA.md
|
3361e2deba
docs: update: improve the Fedoa CUDA guide (#12536)
|
há 9 meses atrás |
|
OPENCL.md
|
5e90233bdb
opencl: update doc (#17011)
|
há 2 meses atrás |
|
SYCL.md
|
279cef27c2
added note for old Intel hardware pre sycl (#18017)
|
há 1 mês atrás |
|
ZenDNN.md
|
017761daf5
ggml-zendnn : add ZenDNN backend for AMD CPUs (#17690)
|
há 1 mês atrás |
|
zDNN.md
|
017761daf5
ggml-zendnn : add ZenDNN backend for AMD CPUs (#17690)
|
há 1 mês atrás |
Alfred
ce734a8a2f
ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977)