@@ -17,7 +17,7 @@ High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisp
1717- Plain C/C++ implementation without dependencies
1818- Apple Silicon first-class citizen - optimized via ARM NEON, Accelerate framework, Metal and [ Core ML] ( #core-ml-support )
1919- AVX intrinsics support for x86 architectures
20- - VSX intrinsics support for POWER architectures
20+ - [ VSX intrinsics support for POWER architectures] ( #power-vsx-intrinsics )
2121- Mixed F16 / F32 precision
2222- [ Integer quantization support] ( #quantization )
2323- Zero memory allocations at runtime
@@ -139,6 +139,20 @@ make -j large-v3-turbo
139139| medium | 1.5 GiB | ~ 2.1 GB |
140140| large | 2.9 GiB | ~ 3.9 GB |
141141
142+ ## POWER VSX Intrinsics
143+
144+ ` whisper.cpp ` supports POWER architectures and includes code which
145+ significantly speeds operation on Linux running on POWER9/10, making it
146+ capable of faster-than-realtime transcription on underclocked Raptor
147+ Talos II. Ensure you have a BLAS package installed, and replace the
148+ standard cmake setup with:
149+
150+ ``` bash
151+ # build with GGML_BLAS defined
152+ cmake -B build -DGGML_BLAS=1
153+ cmake --build build --config Release
154+ ./build/bin/whisper-cli [ .. etc .. ]
155+
142156# # Quantization
143157
144158` whisper.cpp` supports integer quantization of the Whisper ` ggml` models.
0 commit comments