Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Running

App Files Files Community

whisper.cpp / ggml-cuda.cu

JohannesGaessler's picture

JohannesGaessler

CUDA: faster q8_0 -> f16 dequantization (llama/4895)

0a1a178 unverified almost 2 years ago

423 kB

File too large to display, you can check the raw version instead.