Hugging Face's logo

Spaces:
Xenobd
/
whisper.cpp
Running

App Files Community
whisper.cpp / ggml /src /ggml-hip

Commit History

HIP: disable rocwmma on gfx12 by default until rocm 7.0 (llama/14202)
f95736f

uvos commited on

CUDA/HIP: Share the same unified memory allocation logic. (llama/12934)
143cb70

David Huang commited on

HIP: implement FlashAttention via rocWMMA for CDNA and RDNA3+ (llama/12032)
a027c1d

David Huang commited on

CUDA: app option to compile without FlashAttention (llama/12025)
fbc5f16

JohannesGaessler commited on

HIP: force max threads per block to be 1024 (llama/11621)
f509509

fxzjshm commited on

CUDA: use mma PTX instructions for FlashAttention (llama/11583)
f328957

JohannesGaessler Diego Devesa commited on

HIP: require at least HIP 5.5
72c425b

uvos commited on

Hip: disable VMM on hip as it seams that it dosent work in some configurations (llama/11420)
2cc4df4

uvos commited on

hip : Add hipGraph and VMM support to ROCM (llama/11362)
089afa0

uvos commited on

ggml : do not define GGML_USE_CUDA when building with GGML_BACKEND_DL (llama/11211)
79f750d

rgerganov commited on

ggml : add support for dynamic loading of backends (llama/10469)
b73266f

Diego Devesa ggerganov commited on

CUDA: remove DMMV, consolidate F16 mult mat vec (llama/10318)
e446f60

JohannesGaessler commited on

ggml : build backends as libraries (llama/10256)
3dc93f3

Diego Devesa ggerganov R0CKSTAR commited on