root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-11 13:30:35 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

metal : support default.metallib load & reuse code for swift package (#3522)

Browse Source 
* metal : support load default.metallib & reuse code for swift package

* metal : use SWIFT_PACKAGE def instead of define GGML_SWIFT
This commit is contained in:
Jhen-Jie Hong 2023-10-07 03:40:27 -05:00 committed by GitHub
parent 0e797c2fc5
commit c26765a0a1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 34 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -10,6 +10,7 @@
*.gcno
*.gcda
*.dot
*.metallib
.DS_Store
.build/
.cache/

8
Package.swift
View File

@ -10,15 +10,18 @@ let platforms: [SupportedPlatform]? = [
.tvOS(.v14)
]
let exclude: [String] = []
let additionalSources: [String] = ["ggml-metal.m", "ggml-metal.metal"]
let resources: [Resource] = [
.process("ggml-metal.metal")
]
let additionalSources: [String] = ["ggml-metal.m"]
let additionalSettings: [CSetting] = [
.unsafeFlags(["-fno-objc-arc"]),
.define("GGML_SWIFT"),
.define("GGML_USE_METAL")
]
#else
let platforms: [SupportedPlatform]? = nil
let exclude: [String] = ["ggml-metal.metal"]
let resources: [Resource] = []
let additionalSources: [String] = []
let additionalSettings: [CSetting] = []
#endif
@ -40,6 +43,7 @@ let package = Package(
"ggml-alloc.c",
"k_quants.c",
] + additionalSources,
resources: resources,
publicHeadersPath: "spm-headers",
cSettings: [
.unsafeFlags(["-Wno-shorten-64-to-32"]),

66
ggml-metal.m
View File

@ -185,56 +185,44 @@ struct ggml_metal_context * ggml_metal_init(int n_cb) {
ctx->d_queue = dispatch_queue_create("ggml-metal", DISPATCH_QUEUE_CONCURRENT);
#ifdef GGML_SWIFT
// load the default.metallib file
// load library
{
NSError * error = nil;
NSBundle * bundle = [NSBundle bundleForClass:[GGMLMetalClass class]];
NSString * llamaBundlePath = [bundle pathForResource:@"llama_llama" ofType:@"bundle"];
NSBundle * llamaBundle = [NSBundle bundleWithPath:llamaBundlePath];
NSString * libPath = [llamaBundle pathForResource:@"default" ofType:@"metallib"];
NSURL * libURL = [NSURL fileURLWithPath:libPath];
// Load the metallib file into a Metal library
ctx->library = [ctx->device newLibraryWithURL:libURL error:&error];
if (error) {
GGML_METAL_LOG_ERROR("%s: error: %s\n", __func__, [[error description] UTF8String]);
return NULL;
}
}
NSBundle * bundle = nil;
#ifdef SWIFT_PACKAGE
bundle = SWIFTPM_MODULE_BUNDLE;
#else
UNUSED(msl_library_source);
// read the source from "ggml-metal.metal" into a string and use newLibraryWithSource
{
bundle = [NSBundle bundleForClass:[GGMLMetalClass class]];
#endif
NSError * error = nil;
NSString * libPath = [bundle pathForResource:@"default" ofType:@"metallib"];
if (libPath != nil) {
NSURL * libURL = [NSURL fileURLWithPath:libPath];
GGML_METAL_LOG_INFO("%s: loading '%s'\n", __func__, [libPath UTF8String]);
ctx->library = [ctx->device newLibraryWithURL:libURL error:&error];
} else {
GGML_METAL_LOG_INFO("%s: default.metallib not found, loading from source\n", __func__);
//NSString * path = [[NSBundle mainBundle] pathForResource:@"../../examples/metal/metal" ofType:@"metal"];
NSBundle * bundle = [NSBundle bundleForClass:[GGMLMetalClass class]];
NSString * path = [bundle pathForResource:@"ggml-metal" ofType:@"metal"];
GGML_METAL_LOG_INFO("%s: loading '%s'\n", __func__, [path UTF8String]);
NSString * src = [NSString stringWithContentsOfFile:path encoding:NSUTF8StringEncoding error:&error];
if (error) {
GGML_METAL_LOG_ERROR("%s: error: %s\n", __func__, [[error description] UTF8String]);
return NULL;
}
NSString * sourcePath = [bundle pathForResource:@"ggml-metal" ofType:@"metal"];
GGML_METAL_LOG_INFO("%s: loading '%s'\n", __func__, [sourcePath UTF8String]);
NSString * src = [NSString stringWithContentsOfFile:sourcePath encoding:NSUTF8StringEncoding error:&error];
if (error) {
GGML_METAL_LOG_ERROR("%s: error: %s\n", __func__, [[error description] UTF8String]);
return NULL;
}
MTLCompileOptions* options = nil;
#ifdef GGML_QKK_64
MTLCompileOptions* options = [MTLCompileOptions new];
options.preprocessorMacros = @{ @"QK_K" : @(64) };
ctx->library = [ctx->device newLibraryWithSource:src options:options error:&error];
#else
ctx->library = [ctx->device newLibraryWithSource:src options:nil error:&error];
options = [MTLCompileOptions new];
options.preprocessorMacros = @{ @"QK_K" : @(64) };
#endif
ctx->library = [ctx->device newLibraryWithSource:src options:options error:&error];
}
if (error) {
GGML_METAL_LOG_ERROR("%s: error: %s\n", __func__, [[error description] UTF8String]);
return NULL;
}
}
#endif
// load kernels
{
@ -437,7 +425,7 @@ static id<MTLBuffer> ggml_metal_get_buffer(struct ggml_metal_context * ctx, stru
for (int i = 0; i < ctx->n_buffers; ++i) {
const int64_t ioffs = (int64_t) t->data - (int64_t) ctx->buffers[i].data;
//metal_printf("ioffs = %10ld, tsize = %10ld, sum = %10ld, ctx->buffers[%d].size = %10ld, name = %s\n", ioffs, tsize, ioffs + tsize, i, ctx->buffers[i].size, ctx->buffers[i].name);
//GGML_METAL_LOG_INFO("ioffs = %10ld, tsize = %10ld, sum = %10ld, ctx->buffers[%d].size = %10ld, name = %s\n", ioffs, tsize, ioffs + tsize, i, ctx->buffers[i].size, ctx->buffers[i].name);
if (ioffs >= 0 && ioffs + tsize <= (int64_t) ctx->buffers[i].size) {
*offs = (size_t) ioffs;