@@ -17,7 +17,7 @@ High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisp
17
17
- Plain C/C++ implementation without dependencies
18
18
- Apple Silicon first-class citizen - optimized via ARM NEON, Accelerate framework, Metal and [ Core ML] ( #core-ml-support )
19
19
- AVX intrinsics support for x86 architectures
20
- - VSX intrinsics support for POWER architectures
20
+ - [ VSX intrinsics support for POWER architectures] ( #power-vsx-intrinsics )
21
21
- Mixed F16 / F32 precision
22
22
- [ Integer quantization support] ( #quantization )
23
23
- Zero memory allocations at runtime
@@ -139,6 +139,20 @@ make -j large-v3-turbo
139
139
| medium | 1.5 GiB | ~ 2.1 GB |
140
140
| large | 2.9 GiB | ~ 3.9 GB |
141
141
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
+
142
156
# # Quantization
143
157
144
158
` whisper.cpp` supports integer quantization of the Whisper ` ggml` models.
0 commit comments