Hugging Face's logo

Spaces:
Xenobd
/
whisper.cpp
Running

App Files Community
whisper.cpp / ggml /include

Commit History

CPU/CUDA: Gemma 2 FlashAttention support (llama/8542)
fb8ae8b

JohannesGaessler commited on

llama : simplify Mamba with advanced batch splits (llama/8526)
f1abcb4

compilade ggerganov commited on

ggml : move rope type enum to ggml.h (llama/8949)
9d45f48

danbev slaren commited on

feat: ref. cross entropy, add CUDA, fix grad test (ggml/929)
e1e87a3

JohannesGaessler commited on

examples: add MNIST training + missing ops
0828065

JohannesGaessler commited on

feat: add new `sin` and `cos` operators (ggml/919)
f541d31

Ronsor ggerganov commited on

ggml : add CANN backend (llama/0)
7c34a03

hipudding commited on

ggml : add epsilon as a parameter for group_norm (llama/8818)
d003891

mollysama commited on

Fix conversion of unnormalized BF16->BF16 weights (llama/7843)
8b10f59

Sigbjørn Skjæret compilade commited on

feat: Support Moore Threads GPU (llama/8383)
a35db11

yeahdongcn commited on

metal : add abort callback (ggml/905)
b822172

conradev commited on

ggml : move c parameter comment to ggml_rope_ext (ggml/901)
6d34596

danbev commited on

ggml : reduce hash table reset cost (llama/8698)
9808fbf

slaren commited on

ggml : add and use ggml_cpu_has_llamafile() (llama/8664)
efcca56

ggerganov commited on

CUDA: fix partial offloading for ne0 % 256 != 0 (llama/8572)
afc137c

JohannesGaessler commited on

ggml : minor naming changes (llama/8433)
e0c6dff

ggerganov commited on

ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (llama/5780)
9509586

Dibakar Gope commited on

Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (llama/8258)
cc49462

HanClinto commited on

whisper : reorganize source code + improve CMake (#2256)
f75c2e3
unverified

ggerganov commited on