extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-01 07:25:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

cmake : fix compile assumptions for power9/etc (#2777)

Browse Source 
* Add small comment re: VSX to readme

Co-authored-by: midnight <midnight@example.com>
This commit is contained in:
midnight 2025-02-05 04:41:10 -08:00 committed by GitHub
parent 33ea03f131
commit 46d07b9c85
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 22 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

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

18
ggml/src/ggml-cpu/CMakeLists.txt
View File

@ -279,19 +279,15 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
endif()
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "ppc64")
message(STATUS "PowerPC detected")
execute_process(COMMAND bash -c "grep POWER10 /proc/cpuinfo | head -n 1" OUTPUT_VARIABLE POWER10_M)
string(FIND "${POWER10_M}" "POWER10" substring_index)
if (NOT DEFINED substring_index OR "${substring_index}" STREQUAL "")
set(substring_index -1)
endif()
if (${substring_index} GREATER_EQUAL 0)
list(APPEND ARCH_FLAGS -mcpu=power10)
execute_process(COMMAND bash -c "grep POWER /proc/cpuinfo | head -n 1" OUTPUT_VARIABLE POWER_M)
if (${POWER_M} MATCHES "POWER10")
list(APPEND ARCH_FLAGS -mcpu=power10)
elseif (${POWER_M} MATCHES "POWER9")
list(APPEND ARCH_FLAGS -mcpu=power9)
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "ppc64le")
list(APPEND ARCH_FLAGS -mcpu=powerpc64le)
list(APPEND ARCH_FLAGS -mcpu=powerpc64le -mtune=native)
else()
list(APPEND ARCH_FLAGS -mcpu=native -mtune=native)
# TODO: Add targets for Power8/Power9 (Altivec/VSX) and Power10(MMA) and query for big endian systems (ppc64/le/be)
list(APPEND ARCH_FLAGS -mcpu=powerpc64 -mtune=native)
endif()
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "loongarch64")
message(STATUS "loongarch64 detected")