Spaces:

Duplicated from natasa365/whisper.cpp

Xenobd
/

whisper.cpp

Running

App Files Files Community

whisper.cpp / ggml-cuda /mmq.cuh

Commit History

CUDA: faster q2_K, q3_K MMQ + int8 tensor cores (llama/7921)

5931562

JohannesGaessler commited on Jun 14, 2024

CUDA: int8 tensor cores for MMQ (q4_K, q5_K, q6_K) (llama/7860)

154bf2b

JohannesGaessler commited on Jun 11, 2024

CUDA: use tensor cores for MMQ (llama/7676)

78a5b67

JohannesGaessler commited on Jun 10, 2024

CUDA: revise q8_1 data layout for mul_mat_q (llama/7824)

fcfd59e

JohannesGaessler commited on Jun 9, 2024

CUDA: refactor mmq, dmmv, mmvq (llama/7716)

849ff52

JohannesGaessler commited on Jun 5, 2024

sync : ggml (#2001)

cbbfa9e
unverified

ggerganov commited on Mar 27, 2024