Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Running

App Files Files Community

whisper.cpp / ggml /src /ggml-cpu

2.33 MB

100 contributors

History: 151 commits

am17an's picture

Add Conv2d for CPU (llama/14388)

68eb27a 6 months ago

amx
ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317) 6 months ago
arch
ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317) 6 months ago
cmake
ggml : build backends as libraries (llama/10256) about 1 year ago
kleidiai
ggml-cpu : split arch-specific implementations (llama/13892) 7 months ago
llamafile
ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317) 6 months ago
CMakeLists.txt

26.7 kB

ggml-cpu: sycl: Re-enable exp f16 (llama/14462) 6 months ago
arch-fallback.h

10.8 kB

ggml-cpu : remove the weak alias trick (llama/14221) 6 months ago
binary-ops.cpp

6.84 kB

cpu: de-duplicate some of the operators and refactor (ggml/1144) 9 months ago
binary-ops.h

518 Bytes

cpu: de-duplicate some of the operators and refactor (ggml/1144) 9 months ago
common.h

1.85 kB

ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317) 6 months ago
ggml-cpu-impl.h

12.8 kB

ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317) 6 months ago
ggml-cpu.c

118 kB

Add Conv2d for CPU (llama/14388) 6 months ago
ggml-cpu.cpp

22.8 kB

ggml : add ggml_set_rows (llama/14274) 6 months ago
hbm.cpp

2 kB

ggml-cpu : split arch-specific implementations (llama/13892) 7 months ago
hbm.h

155 Bytes

ggml-cpu : split arch-specific implementations (llama/13892) 7 months ago
ops.cpp

332 kB

Add Conv2d for CPU (llama/14388) 6 months ago
ops.h

8.82 kB

Add Conv2d for CPU (llama/14388) 6 months ago
quants.c

39.1 kB

ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317) 6 months ago
quants.h

9.14 kB

ggml-cpu : rework weak alias on apple targets (llama/14146) 6 months ago
repack.cpp

61.4 kB

ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317) 6 months ago
repack.h

5.96 kB

ggml-cpu : remove the weak alias trick (llama/14221) 6 months ago
simd-mappings.h

48 kB

ggml-cpu: enable IBM NNPA Vector Intrinsics (llama/14317) 6 months ago
traits.cpp

1.23 kB

ggml-cpu : split arch-specific implementations (llama/13892) 7 months ago
traits.h

1.16 kB

ggml-cpu : split arch-specific implementations (llama/13892) 7 months ago
unary-ops.cpp

5.79 kB

cpu: de-duplicate some of the operators and refactor (ggml/1144) 9 months ago
unary-ops.h

1.73 kB

cpu: de-duplicate some of the operators and refactor (ggml/1144) 9 months ago
vec.cpp

12.7 kB

ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158) 6 months ago
vec.h

42.2 kB

ggml : fix unmerged GGML_FPxx_TO_FPxx refactoring (llama/14443) 6 months ago