ggml-org/whisper.cpp

NPU support in whisper.cpp

Open

Aperta il 27 nov 2023

Vedi su GitHub
 (18 commenti) (12 reazioni) (0 assegnatari)C++ (49.693 star) (5535 fork)batch import
good first issueperformanceresearch🔬

Descrizione

Christmas is coming soon, and I want to take some time to research something interesting, such as edge low-power inference. Although current whisper.cpp can run on Raspberry Pi, the inference performance cannot achieve real-time transcription. Fortunately, there are now some development boards that use processors with NPUs, which can be used to achieve real-time transcription of large models. My primary goal is to first support RK3566 and RK3588.

Roadmap:

  • MatMul offloading
  • Conv-Gelu offloading
  • LayerNorm offloading ...

Reference:

https://github.com/rockchip-linux/rknpu2

Guida contributor

Tech stack
cpp
Dominio
machine learningperformance
Tipo issue
feature
DifficoltàQuanto dovrebbe essere impegnativa per un nuovo contributor.
5
Tempo stimatoTempo stimato per completare e verificare uno scope piccolo.
over 1 week
Stato attivitàQuanto è probabile che la issue sia ancora attiva e reviewable.
active
ChiarezzaQuanto chiaramente la issue descrive problema, scope e risultato atteso.
mostly clear
Prerequisiti
C++ programmingNeural network inference basicsNPU architecture knowledgeRK3566/RK3588 familiarity
Adatta ai principiantiQuanto la issue è adatta a contributor alla prima esperienza.
20
Direzione di ricerca
The issue proposes adding NPU support for RK3566 and RK3588, with a roadmap for offloading MatMul, Conv Gelu, and LayerNorm. Research should focus on integrating with the Rockchip RKNN toolkit (rknpu2) and modifying the whisper.cpp backend to delegate these operations to the NPU. Investigate existing ggml backend implementations for similar hardware and adapt the build system. Review the linked discussion on Raspberry Pi for performance baselines.