extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-19 10:32:12 +02:00
Code Issues Packages Projects Releases Wiki Activity

whisper : Metal and ggml-alloc support (#1270)

Browse Source 
* metal : init

* whisper : factor out graph builds

* whisper : allocate encoder and decoder using ggml-alloc

* whisper : ggml-alloc is now supported

* whisper : CoreML support ggml-alloc

* build : fix ggml-alloc

* ios : update submodule

* extra : update sync-ggml.sh script to also sync ggml-alloc

* ci : see if this is causing the crash

* whisper : refactor ggml-alloc init

* whisper.android : try to fix build

* whisper : initial Metal version

* ci : try to debug vmem issue

* metal : decoder works on GPU!

* metal : add multi-decoder support

* ggml : fix ggml_nbytes (probably temp solution)

* metal : run "cross" step on the GPU

* whisper : remove ggml_repeat in the encoder

* whisper : offload the Encoder to Metal

* ggml : use simpler ggml_bytes() implementation

* ggml-alloc : try to make CI happy by reducing vram to 128GB

* whisper : add whisper_allocr to wrap ggml_allocr

* whisper : factor out alloc init in a function

* cmake : update to support Metal build

* whisper : add <functional> header

* objc : fix build (no Metal yet)

* ios : add Metal support

* swiftui : fix build

* metal : speed-up KQ multiplication

* metal : sync latest llama.cpp kernels

* readme : add Metal info

* ios : update submodule

* coreml : add code to toggle Core ML config (CPU, ANE, GPU)

* bench : fix timings by running a pre-heat

* bench : start benching the decoder

* whisper : add ggml_mul_mat_pad

* bench : fix uninitialized vars

* whisper : add comment for disabling mul-mat padding

* whisper : add description of ggml_mul_mat_pad

* whisper : clean-up ggml_mul_mat_pad

* metal : remove the "concurrent" flag

* bench : variable n_past

* ios : update SPM package
This commit is contained in:
Georgi Gerganov
2023-09-15 12:18:18 +03:00
committed by GitHub
parent 3fec2119e6
commit 93935980f8
18 changed files with 1855 additions and 1252 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -11,14 +11,14 @@ Beta: [v1.4.2](https://github.com/ggerganov/whisper.cpp/releases/tag/v1.4.2) / S
High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisper) automatic speech recognition (ASR) model:
- Plain C/C++ implementation without dependencies
- Apple silicon first-class citizen - optimized via ARM NEON, Accelerate framework and [Core ML](https://github.com/ggerganov/whisper.cpp#core-ml-support)
- Apple Silicon first-class citizen - optimized via ARM NEON, Accelerate framework, Metal and [Core ML](https://github.com/ggerganov/whisper.cpp#core-ml-support)
- AVX intrinsics support for x86 architectures
- VSX intrinsics support for POWER architectures
- Mixed F16 / F32 precision
- [4-bit and 5-bit integer quantization support](https://github.com/ggerganov/whisper.cpp#quantization)
- Low memory usage (Flash Attention)
- Zero memory allocations at runtime
- Runs on the CPU
- Support for CPU-only inference
- [Partial GPU support for NVIDIA via cuBLAS](https://github.com/ggerganov/whisper.cpp#nvidia-gpu-support-via-cublas)
- [Partial OpenCL GPU support via CLBlast](https://github.com/ggerganov/whisper.cpp#opencl-gpu-support-via-clblast)
- [BLAS CPU support via OpenBLAS](https://github.com/ggerganov/whisper.cpp#blas-cpu-support-via-openblas)
@@ -50,6 +50,10 @@ You can also easily make your own offline voice assistant application: [command]
https://user-images.githubusercontent.com/1991296/204038393-2f846eae-c255-4099-a76d-5735c25c49da.mp4
On Apply Silicon, the inference runs fully on the GPU via Metal:
https://github.com/ggerganov/whisper.cpp/assets/1991296/c82e8f86-60dc-49f2-b048-d2fdbd6b5225
Or you can even run it straight in the browser: [talk.wasm](examples/talk.wasm)
## Implementation details