Skip to content

pullrequests Search Results · repo:ggerganov/whisper.cpp language:C

Filter by

616 results
 (88 ms)

616 results

inggerganov/whisper.cpp (press backspace or delete to remove)

ggerganov/whisper.cpp
whisper : reorganize source code + improve CMake

ref https://github.com/ggerganov/llama.cpp/pull/8006
  • ggerganov
  • Opened 
    26 days ago
  • #2256

ggerganov/whisper.cpp
whisper: optimize fft() function

In log_mel_spectrogram_worker_thread() function, we allocate enough memory for fft_in and fft_out variable, and then we can avoid allocating memory for even, odd, even_fft and odd_fft in fft(). In my testing, ...
  • mkycoder
  • 2
  • Opened 
    on Jun 18
  • #2242

ggerganov/whisper.cpp
use sched in whisper_allocr

The target is https://github.com/ggerganov/whisper.cpp/pull/2239 Not sure if this is better, but it works. Increasing the number of threads of the BLAS backend seem to results in better performance with ...
  • slaren
  • 1
  • Opened 
    on Jun 16
  • #2240

ggerganov/whisper.cpp
whisper : use ggml_backend_sched

target branch: https://github.com/ggerganov/whisper.cpp/tree/sync-blas Using BLAS just in the Encoder since it involves large matrices
  • ggerganov
  • 10
  • Opened 
    on Jun 16
  • #2239

ggerganov/whisper.cpp
sync : ggml-blas

TODO: - [x] update CMake / Makefile builds - [x] try to introduce ggml_backend_sched: https://github.com/ggerganov/whisper.cpp/pull/2239
  • ggerganov
  • 1
  • Opened 
    on Jun 16
  • #2238

ggerganov/whisper.cpp
sync : ggml

  • ggerganov
  • Opened 
    on Jun 16
  • #2237

ggerganov/whisper.cpp
whisper : use ggml-cuda in mel calc, set appropriate device

- fix issues where whisper may be set to run on a device which is not the current one for all mel_calc calls. - workaround for #2230 as opposed to #2235 : forbid mel_calc_cuda if device cc is below ...
  • iboB
  • 1
  • Opened 
    on Jun 12
  • #2236

ggerganov/whisper.cpp
cuda : avoid async allocs in CUDA mel code

fix #2230
  • ggerganov
  • 2
  • Opened 
    on Jun 12
  • #2235

ggerganov/whisper.cpp
cuda : fix HIPBLAS build

fix #2229
  • ggerganov
  • Opened 
    on Jun 11
  • #2234

ggerganov/whisper.cpp
ci : fix CUDA builds

Same as: https://github.com/ggerganov/llama.cpp/pull/7861
  • ggerganov
  • Opened 
    on Jun 11
  • #2232