whisper.cpp/coreml/whisper-encoder.mm
Georgi Gerganov 93935980f8
whisper : Metal and ggml-alloc support (#1270)
* 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
2023-09-15 12:18:18 +03:00

72 lines
2.1 KiB
Plaintext

#if !__has_feature(objc_arc)
#error This file must be compiled with automatic reference counting enabled (-fobjc-arc)
#endif
#import "whisper-encoder.h"
#import "whisper-encoder-impl.h"
#import <CoreML/CoreML.h>
#include <stdlib.h>
#if __cplusplus
extern "C" {
#endif
struct whisper_coreml_context {
const void * data;
};
struct whisper_coreml_context * whisper_coreml_init(const char * path_model) {
NSString * path_model_str = [[NSString alloc] initWithUTF8String:path_model];
NSURL * url_model = [NSURL fileURLWithPath: path_model_str];
// select which device to run the Core ML model on
MLModelConfiguration *config = [[MLModelConfiguration alloc] init];
config.computeUnits = MLComputeUnitsCPUAndGPU;
//config.computeUnits = MLComputeUnitsCPUAndNeuralEngine;
//config.computeUnits = MLComputeUnitsAll;
const void * data = CFBridgingRetain([[whisper_encoder_impl alloc] initWithContentsOfURL:url_model configuration:config error:nil]);
if (data == NULL) {
return NULL;
}
whisper_coreml_context * ctx = new whisper_coreml_context;
ctx->data = data;
return ctx;
}
void whisper_coreml_free(struct whisper_coreml_context * ctx) {
CFRelease(ctx->data);
delete ctx;
}
void whisper_coreml_encode(
const whisper_coreml_context * ctx,
float * mel,
float * out) {
MLMultiArray * inMultiArray = [
[MLMultiArray alloc] initWithDataPointer: mel
shape: @[@1, @80, @3000]
dataType: MLMultiArrayDataTypeFloat32
strides: @[@(240000), @(3000), @1]
deallocator: nil
error: nil
];
@autoreleasepool {
whisper_encoder_implOutput * outCoreML = [(__bridge id) ctx->data predictionFromLogmel_data:inMultiArray error:nil];
memcpy(out, outCoreML.output.dataPointer, outCoreML.output.count * sizeof(float));
}
}
#if __cplusplus
}
#endif