| .. |
|
ggml-alloc.h
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
il y a 10 mois |
|
ggml-backend.h
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
il y a 10 mois |
|
ggml-blas.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
il y a 1 an |
|
ggml-cann.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
il y a 1 an |
|
ggml-cpp.h
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
il y a 1 an |
|
ggml-cpu.h
|
07d1572347
ggml-cpu: Faster IQ1 mul_mat_vec on AVX2 using BMI2 instructions (#12154)
|
il y a 10 mois |
|
ggml-cuda.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
il y a 1 an |
|
ggml-kompute.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
il y a 1 an |
|
ggml-metal.h
|
68ff663a04
repo : update links to new url (#11886)
|
il y a 11 mois |
|
ggml-opencl.h
|
a76c56fa1a
Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
|
il y a 1 an |
|
ggml-opt.h
|
8a43e940ab
ggml: new optimization interface (ggml/988)
|
il y a 1 an |
|
ggml-rpc.h
|
ab6ab8f809
rpc : send hash when tensor data is above some fixed threshold (#12496)
|
il y a 9 mois |
|
ggml-sycl.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
il y a 1 an |
|
ggml-vulkan.h
|
c2a67efe38
vulkan: Make Vulkan optional at runtime (#11493). (#11494)
|
il y a 11 mois |
|
ggml.h
|
b4ae50810e
metal : improve FA + improve MoE (#12612)
|
il y a 9 mois |
|
gguf.h
|
53ff6b9b9f
GGUF: C++ refactor, backend support, misc fixes (#11030)
|
il y a 1 an |
Georgi Gerganov
b4ae50810e
metal : improve FA + improve MoE (#12612)