node-llama-cpp 3.0.0-beta.2 → 3.0.0-beta.21

package/llama/binariesGithubRelease.json

@@ -1,3 +1,3 @@
 {
-    "release": "b1892"
+    "release": "b2929"
 }

package/llama/gpuInfo/cuda-gpu-info.cu

@@ -0,0 +1,120 @@
+#include <stddef.h>
+#include <vector>
+#include <string>
+
+#if defined(GPU_INFO_USE_HIPBLAS)
+#include <hip/hip_runtime.h>
+#include <hipblas/hipblas.h>
+#define cudaGetDevice hipGetDevice
+#define cudaGetDeviceCount hipGetDeviceCount
+#define cudaGetErrorString hipGetErrorString
+#define cudaMemGetInfo hipMemGetInfo
+#define cudaSetDevice hipSetDevice
+#define cudaSuccess hipSuccess
+#else
+#include <cuda_runtime.h>
+#include <cuda.h>
+#endif
+
+
+typedef void (*gpuInfoCudaErrorLogCallback_t)(const char* message);
+
+bool gpuInfoSetCudaDevice(const int device, gpuInfoCudaErrorLogCallback_t errorLogCallback) {
+    int current_device;
+    auto getDeviceResult = cudaGetDevice(&current_device);
+
+    if (getDeviceResult != cudaSuccess) {
+        errorLogCallback(cudaGetErrorString(getDeviceResult));
+        return false;
+    }
+
+    if (device == current_device) {
+        return true;
+    }
+
+    const auto setDeviceResult = cudaSetDevice(device);
+
+    if (setDeviceResult != cudaSuccess) {
+        errorLogCallback(cudaGetErrorString(setDeviceResult));
+        return false;
+    }
+
+    return true;
+}
+
+bool gpuInfoGetCudaDeviceInfo(int device, size_t * total, size_t * used, gpuInfoCudaErrorLogCallback_t errorLogCallback) {
+    gpuInfoSetCudaDevice(device, errorLogCallback);
+
+    size_t freeMem;
+    size_t totalMem;
+    auto getMemInfoResult = cudaMemGetInfo(&freeMem, &totalMem);
+
+    if (getMemInfoResult != cudaSuccess) {
+        errorLogCallback(cudaGetErrorString(getMemInfoResult));
+        return false;
+    }
+
+    *total = totalMem;
+    *used = totalMem - freeMem;
+
+    return true;
+}
+
+int gpuInfoGetCudaDeviceCount(gpuInfoCudaErrorLogCallback_t errorLogCallback) {
+    int deviceCount;
+    auto getDeviceCountResult = cudaGetDeviceCount(&deviceCount);
+
+    if (getDeviceCountResult != cudaSuccess) {
+        errorLogCallback(cudaGetErrorString(getDeviceCountResult));
+        return -1;
+    }
+
+    return deviceCount;
+}
+
+bool gpuInfoGetTotalCudaDevicesInfo(size_t * total, size_t * used, gpuInfoCudaErrorLogCallback_t errorLogCallback) {
+    int deviceCount = gpuInfoGetCudaDeviceCount(errorLogCallback);
+
+    if (deviceCount < 0) {
+        return false;
+    }
+
+    size_t usedMem = 0;
+    size_t totalMem = 0;
+
+    for (int i = 0; i < deviceCount; i++) {
+        size_t deviceUsedMem;
+        size_t deviceTotalMem;
+
+        if (!gpuInfoGetCudaDeviceInfo(i, &deviceTotalMem, &deviceUsedMem, errorLogCallback)) {
+            return false;
+        }
+
+        usedMem += deviceUsedMem;
+        totalMem += deviceTotalMem;
+    }
+
+    *total = totalMem;
+    *used = usedMem;
+
+    return true;
+}
+
+void gpuInfoGetCudaDeviceNames(std::vector<std::string> * deviceNames, gpuInfoCudaErrorLogCallback_t errorLogCallback) {
+    int deviceCount = gpuInfoGetCudaDeviceCount(errorLogCallback);
+
+    if (deviceCount < 0) {
+        return;
+    }
+
+    for (int i = 0; i < deviceCount; i++) {
+        cudaDeviceProp prop;
+        auto getDevicePropertiesResult = cudaGetDeviceProperties(&prop, i);
+
+        if (getDevicePropertiesResult != cudaSuccess) {
+            errorLogCallback(cudaGetErrorString(getDevicePropertiesResult));
+        } else {
+            (*deviceNames).push_back(std::string(prop.name));
+        }
+    }
+}

package/llama/gpuInfo/cuda-gpu-info.h

@@ -0,0 +1,10 @@
+#pragma once
+
+#include <stddef.h>
+#include <vector>
+#include <string>
+
+typedef void (*gpuInfoCudaErrorLogCallback_t)(const char* message);
+
+bool gpuInfoGetTotalCudaDevicesInfo(size_t * total, size_t * used, gpuInfoCudaErrorLogCallback_t errorLogCallback);
+void gpuInfoGetCudaDeviceNames(std::vector<std::string> * deviceNames, gpuInfoCudaErrorLogCallback_t errorLogCallback);

package/llama/gpuInfo/metal-gpu-info.h

@@ -0,0 +1,8 @@
+#pragma once
+
+#include <stdint.h>
+#include <string>
+#include <vector>
+
+void getMetalGpuInfo(uint64_t * total, uint64_t * used);
+void getMetalGpuDeviceNames(std::vector<std::string> * deviceNames);

package/llama/gpuInfo/metal-gpu-info.mm

@@ -0,0 +1,30 @@
+#include <stdint.h>
+#include <vector>
+#include <string>
+#import <Metal/Metal.h>
+
+void getMetalGpuInfo(uint64_t * total, uint64_t * used) {
+    id<MTLDevice> device = MTLCreateSystemDefaultDevice();
+
+    if (device) {
+        *total = device.recommendedMaxWorkingSetSize;
+        *used = device.currentAllocatedSize;
+    } else {
+        *total = 0;
+        *used = 0;
+    }
+
+    [device release];
+    device = nil;
+}
+
+void getMetalGpuDeviceNames(std::vector<std::string> * deviceNames) {
+    NSArray<id<MTLDevice>> *devices = MTLCopyAllDevices();
+
+    for (id<MTLDevice> device in devices) {
+        (*deviceNames).push_back(std::string(([NSString stringWithUTF8String:device.name.UTF8String]).UTF8String));
+    }
+
+    [devices release];
+    devices = nil;
+}

package/llama/gpuInfo/vulkan-gpu-info.cpp

@@ -0,0 +1,83 @@
+#include <stddef.h>
+#include <vector>
+
+#include <vulkan/vulkan.hpp>
+
+typedef void (*gpuInfoVulkanWarningLogCallback_t)(const char* message);
+
+static bool enumerateVulkanDevices(size_t* total, size_t* used, bool addDeviceNames, std::vector<std::string> * deviceNames, gpuInfoVulkanWarningLogCallback_t warningLogCallback) {
+    vk::ApplicationInfo appInfo("node-llama-cpp GPU info", 1, "llama.cpp", 1, VK_API_VERSION_1_2);
+    vk::InstanceCreateInfo createInfo(vk::InstanceCreateFlags(), &appInfo, {}, {});
+    vk::Instance instance = vk::createInstance(createInfo);
+
+    auto physicalDevices = instance.enumeratePhysicalDevices();
+
+    size_t usedMem = 0;
+    size_t totalMem = 0;
+
+    for (size_t i = 0; i < physicalDevices.size(); i++) {
+        vk::PhysicalDevice physicalDevice = physicalDevices[i];
+        vk::PhysicalDeviceMemoryProperties memProps = physicalDevice.getMemoryProperties();
+        vk::PhysicalDeviceProperties deviceProps = physicalDevice.getProperties();
+
+        if (deviceProps.deviceType == vk::PhysicalDeviceType::eCpu) {
+            // ignore CPU devices, as we don't want to count RAM from the CPU as VRAM
+            continue;
+        }
+
+        std::vector<vk::ExtensionProperties> extensionProperties = physicalDevice.enumerateDeviceExtensionProperties();
+        bool memoryBudgetExtensionSupported =
+            std::any_of(
+                extensionProperties.begin(),
+                extensionProperties.end(),
+                [](const vk::ExtensionProperties& ext) { return std::string(ext.extensionName.data()) == VK_EXT_MEMORY_BUDGET_EXTENSION_NAME;}
+            );
+
+        if (memoryBudgetExtensionSupported) {
+            vk::PhysicalDeviceMemoryBudgetPropertiesEXT memoryBudgetProperties;
+            vk::PhysicalDeviceMemoryProperties2 memProps2 = {};
+            memProps2.pNext = &memoryBudgetProperties;
+
+            physicalDevice.getMemoryProperties2(&memProps2);
+
+            for (uint32_t i = 0; i < memProps.memoryHeapCount; ++i) {
+                if (memProps.memoryHeaps[i].flags & vk::MemoryHeapFlagBits::eDeviceLocal) {
+                    const auto size = memProps.memoryHeaps[i].size;
+                    totalMem += size;
+                    usedMem += memoryBudgetProperties.heapUsage[i];
+
+                    if (size > 0 && addDeviceNames) {
+                        (*deviceNames).push_back(std::string(deviceProps.deviceName.data()));
+                    }
+
+                    break;
+                }
+            }
+        } else {
+            // VK_EXT_memory_budget extension is not supported, so we cannot determine used memory
+            warningLogCallback(
+                (
+                    "Vulkan VK_EXT_memory_budget extension not supported for device \"" +
+                    std::string(deviceProps.deviceName.data()) + "\", so VRAM info cannot be determained for it"
+                )
+                    .c_str()
+            );
+            return false;
+        }
+    }
+
+    *total = totalMem;
+    *used = usedMem;
+    return true;
+}
+
+bool gpuInfoGetTotalVulkanDevicesInfo(size_t* total, size_t* used, gpuInfoVulkanWarningLogCallback_t warningLogCallback) {
+    return enumerateVulkanDevices(total, used, false, nullptr, warningLogCallback);
+}
+
+bool gpuInfoGetVulkanDeviceNames(std::vector<std::string> * deviceNames, gpuInfoVulkanWarningLogCallback_t warningLogCallback) {
+    size_t vulkanDeviceTotal = 0;
+    size_t vulkanDeviceUsed = 0;
+
+    return enumerateVulkanDevices(&vulkanDeviceTotal, &vulkanDeviceUsed, true, deviceNames, warningLogCallback);
+}

package/llama/gpuInfo/vulkan-gpu-info.h

@@ -0,0 +1,9 @@
+#pragma once
+
+#include <stddef.h>
+#include <vector>
+
+typedef void (*gpuInfoVulkanWarningLogCallback_t)(const char* message);
+
+bool gpuInfoGetTotalVulkanDevicesInfo(size_t* total, size_t* used, gpuInfoVulkanWarningLogCallback_t warningLogCallback);
+bool gpuInfoGetVulkanDeviceNames(std::vector<std::string> * deviceNames, gpuInfoVulkanWarningLogCallback_t warningLogCallback);

package/llama/grammars/README.md

@@ -51,7 +51,7 @@ single-line ::= [^\n]+ "\n"`
 
 ## Sequences and Alternatives
 
-The order of symbols in a sequence matter. For example, in `"1. " move " " move "\n"`, the `"1. "` must come before the first `move`, etc.
+The order of symbols in a sequence matters. For example, in `"1. " move " " move "\n"`, the `"1. "` must come before the first `move`, etc.
 
 Alternatives, denoted by `|`, give different sequences that are acceptable. For example, in `move ::= pawn | nonpawn | castle`, `move` can be a `pawn` move, a `nonpawn` move, or a `castle`.
 
@@ -89,3 +89,13 @@ This guide provides a brief overview. Check out the GBNF files in this directory
 ```
 ./main -m <model> --grammar-file grammars/some-grammar.gbnf -p 'Some prompt'
 ```
+
+## Troubleshooting
+
+Grammars currently have performance gotchas (see https://github.com/ggerganov/llama.cpp/issues/4218).
+
+### Efficient optional repetitions
+
+A common pattern is to allow repetitions of a pattern `x` up to N times.
+
+While semantically correct, the syntax `x? x? x?.... x?` (with N repetitions) will result in extremely slow inference. Instead, you can write `(x (x (x ... (x)?...)?)?)?` (w/ N-deep nesting)

package/llama/grammars/json.gbnf

@@ -15,7 +15,7 @@ array  ::=
 
 string ::=
   "\"" (
-    [^"\\] |
+    [^"\\\x7F\x00-\x1F] |
     "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F]) # escapes
   )* "\"" ws
 

package/llama/grammars/json_arr.gbnf

@@ -24,7 +24,7 @@ array  ::=
 
 string ::=
   "\"" (
-    [^"\\] |
+    [^"\\\x7F\x00-\x1F] |
     "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F]) # escapes
   )* "\"" ws
 

package/llama/llama.cpp.info.json

@@ -0,0 +1,4 @@
+{
+    "tag": "b2929",
+    "llamaCppGithubRepo": "ggerganov/llama.cpp"
+}

package/llama/toolchains/win32.host-x64.target-arm64.cmake

@@ -0,0 +1,41 @@
+set(CMAKE_SYSTEM_NAME Windows)
+set(CMAKE_SYSTEM_PROCESSOR ARM64)
+
+# Look for cl.exe in the Visual Studio installation directories
+set(PROGRAMFILES "$ENV{ProgramFiles}")
+set(PROGRAMFILES_X86 "$ENV{ProgramFiles\(x86\)}")
+
+set(VS_INSTALL_PATHS
+    "${PROGRAMFILES_X86}/Microsoft Visual Studio"
+    "${PROGRAMFILES}/Microsoft Visual Studio"
+    "C:/Program Files (x86)/Microsoft Visual Studio"
+    "C:/Program Files/Microsoft Visual Studio"
+)
+foreach(PATH IN LISTS VS_INSTALL_PATHS)
+    if(CL_EXE_PATH)
+        break()
+    endif()
+
+    file(GLOB_RECURSE FOUND_CL_EXE "${PATH}/*/VC/Tools/MSVC/*/bin/Hostx64/arm64/cl.exe")
+    if(FOUND_CL_EXE)
+        list(GET FOUND_CL_EXE 0 CL_EXE_PATH)
+        break()
+    endif()
+
+    if(CL_EXE_PATH)
+        break()
+    endif()
+
+    file(GLOB_RECURSE FOUND_CL_EXE "${PATH}/**/*/VC/Tools/MSVC/*/bin/Hostx64/arm64/cl.exe")
+    if(FOUND_CL_EXE)
+        list(GET FOUND_CL_EXE 0 CL_EXE_PATH)
+        break()
+    endif()
+endforeach()
+
+if(NOT CL_EXE_PATH)
+    message(FATAL_ERROR "cl.exe not found for ARM architecture.")
+else()
+    set(CMAKE_C_COMPILER "${CL_EXE_PATH}")
+    set(CMAKE_CXX_COMPILER "${CL_EXE_PATH}")
+endif()

package/llamaBins/linux-arm64/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"linux","platformInfo":{"name":"Ubuntu","version":"22.04"},"arch":"arm64","gpu":false,"llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b2929"}}}

package/llamaBins/linux-armv7l/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"linux","platformInfo":{"name":"Ubuntu","version":"22.04"},"arch":"armv7l","gpu":false,"llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b2929"}}}

package/llamaBins/linux-x64/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"linux","platformInfo":{"name":"Ubuntu","version":"22.04"},"arch":"x64","gpu":false,"llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b2929"}}}

package/llamaBins/linux-x64-cuda/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"linux","platformInfo":{"name":"Ubuntu","version":"22.04"},"arch":"x64","gpu":"cuda","llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b2929"}}}

package/llamaBins/linux-x64-vulkan/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"linux","platformInfo":{"name":"Ubuntu","version":"22.04"},"arch":"x64","gpu":"vulkan","llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b2929"}}}

package/llamaBins/mac-arm64-metal/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"mac","platformInfo":{"name":"macOS","version":"21.6.0"},"arch":"arm64","gpu":"metal","llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b2929"}}}

package/llamaBins/mac-x64/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"mac","platformInfo":{"name":"macOS","version":"21.6.0"},"arch":"x64","gpu":false,"llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b2929"}}}

package/llamaBins/win-arm64/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"win","platformInfo":{"name":"Windows","version":"10.0.20348"},"arch":"arm64","gpu":false,"llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b2929"}}}

package/llamaBins/win-x64/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"win","platformInfo":{"name":"Windows","version":"10.0.20348"},"arch":"x64","gpu":false,"llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b2929"}}}

package/llamaBins/win-x64-cuda/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"win","platformInfo":{"name":"Windows","version":"10.0.20348"},"arch":"x64","gpu":"cuda","llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b2929"}}}

package/llamaBins/win-x64-vulkan/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"win","platformInfo":{"name":"Windows","version":"10.0.20348"},"arch":"x64","gpu":"vulkan","llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b2929"}}}

package/package.json

@@ -1,15 +1,16 @@
 {
   "name": "node-llama-cpp",
-  "version": "3.0.0-beta.2",
+  "version": "3.0.0-beta.21",
   "description": "Run AI models locally on your machine with node.js bindings for llama.cpp. Force a JSON schema on the model output on the generation level",
-  "main": "dist/index.js",
+  "main": "./dist/index.js",
   "type": "module",
   "types": "./dist/index.d.ts",
   "bin": {
-    "node-llama-cpp": "./dist/cli/cli.js"
+    "node-llama-cpp": "dist/cli/cli.js"
   },
   "files": [
     "dist/",
+    "templates/packed/",
     "llama/",
     "llamaBins/",
     "package.json",
@@ -41,30 +42,33 @@
   },
   "scripts": {
     "prepare": "[ \"$CI\" = true ] || [ -d '.husky/_' ] || husky install",
+    "postinstall": "node ./dist/cli/cli.js postinstall",
     "prebuild": "rimraf ./dist ./tsconfig.tsbuildinfo",
-    "build": "tsc --build tsconfig.json --force",
+    "build": "tsc --build tsconfig.json --force && npm run build:packTemplates",
+    "build:packTemplates": "vite-node scripts/packTemplates.ts",
     "addPostinstallScript": "npm pkg set scripts.postinstall=\"node ./dist/cli/cli.js postinstall\"",
     "prewatch": "rimraf ./dist ./tsconfig.tsbuildinfo",
     "watch": "tsc --build tsconfig.json --watch --force",
     "cmake-js-llama": "cd llama && cmake-js",
-    "test": "npm run test:typescript && npm run lint:eslint && npm run test:standalone && npm run test:modelDependent",
+    "test": "npm run test:typescript && npm run lint:eslint && npm run test:vitest",
+    "test:vitest": "vitest run ./test",
     "test:standalone": "vitest run ./test/standalone",
     "test:standalone:interactive": "vitest watch ./test/standalone",
     "test:modelDependent": "vitest run ./test/modelDependent",
     "test:modelDependent:interactive": "vitest watch ./test/modelDependent",
     "test:typescript": "tsc --build tsconfig.json --dry --force",
     "lint": "npm run lint:eslint",
-    "lint:eslint": "eslint --ext .js --ext .ts .",
+    "lint:eslint": "eslint --ext .js --ext .ts --report-unused-disable-directives .",
     "format": "npm run lint:eslint -- --fix",
-    "dev:setup:downloadAllTestModels": "node --loader ts-node/esm test/utils/scripts/downloadAllTestModels.ts",
-    "dev:setup": "npm run build && node ./dist/cli/cli.js download && npm run docs:generateTypedoc && npm run dev:setup:downloadAllTestModels",
-    "dev:build": "npm run build && node ./dist/cli/cli.js build",
-    "clean": "rm -rf ./node_modules ./dist ./tsconfig.tsbuildinfo ./test/.models",
-    "docs:generateTypedoc": "typedoc && rimraf ./docs/api/index.md ./docs/api/exports.md",
+    "dev:setup:downloadAllTestModels": "vite-node test/utils/scripts/downloadAllTestModels.ts",
+    "dev:setup": "npm run build && node ./dist/cli/cli.js download --noUsageExample && npm run docs:generateTypedoc && npm run dev:setup:downloadAllTestModels",
+    "dev:build": "npm run build && node ./dist/cli/cli.js build --noUsageExample",
+    "clean": "rm -rf ./node_modules ./dist ./tsconfig.tsbuildinfo ./test/.models ./docs/api ./docs/api-overrides ./templates/packed",
+    "docs:generateTypedoc": "typedoc && rimraf ./docs/api/index.md ./docs/api/globals.md ./docs/api/functions/LlamaText.md && npm run docs:generateTypedoc:overrides",
+    "docs:generateTypedoc:overrides": "typedoc --entryPoints ./src/apiDocsOverrides.ts --out ./docs/api-overrides && copyfiles --flat \"./docs/api-overrides/classes/LlamaText.md\" ./docs/api/classes && rimraf ./docs/api-overrides",
     "docs:dev": "npm run docs:generateTypedoc && vitepress dev",
     "docs:build": "npm run docs:generateTypedoc && vitepress build",
-    "docs:preview": "npm run docs:generateTypedoc && vitepress preview",
-    "postinstall": "node ./dist/cli/cli.js postinstall"
+    "docs:preview": "npm run docs:generateTypedoc && vitepress preview"
   },
   "repository": {
     "type": "git",
@@ -83,10 +87,15 @@
     "gguf",
     "metal",
     "cuda",
+    "vulkan",
     "grammar",
     "json-grammar",
     "json-schema-grammar",
+    "functions",
+    "function-calling",
+    "embedding",
     "temperature",
+    "minP",
     "topK",
     "topP",
     "json-schema",
@@ -106,54 +115,72 @@
   },
   "homepage": "https://withcatai.github.io/node-llama-cpp/",
   "devDependencies": {
-    "@commitlint/cli": "^17.7.1",
-    "@commitlint/config-conventional": "^17.7.0",
+    "@commitlint/cli": "^19.3.0",
+    "@commitlint/config-conventional": "^19.2.2",
     "@semantic-release/exec": "^6.0.3",
-    "@types/cli-progress": "^3.11.0",
+    "@shikijs/vitepress-twoslash": "^1.3.0",
+    "@types/async-retry": "^1.4.8",
+    "@types/bytes": "^3.1.4",
     "@types/cross-spawn": "^6.0.2",
-    "@types/fs-extra": "^11.0.1",
-    "@types/node": "^20.8.4",
-    "@types/uuid": "^9.0.2",
+    "@types/fs-extra": "^11.0.4",
+    "@types/node": "^20.11.29",
+    "@types/proper-lockfile": "^4.1.4",
+    "@types/semver": "^7.5.8",
+    "@types/validate-npm-package-name": "^4.0.2",
     "@types/which": "^3.0.0",
     "@types/yargs": "^17.0.24",
     "@typescript-eslint/eslint-plugin": "^6.3.0",
     "@typescript-eslint/parser": "^6.3.0",
-    "@vitest/coverage-v8": "^0.34.6",
+    "@vitest/coverage-v8": "^1.4.0",
+    "@vitest/ui": "^1.4.0",
+    "copyfiles": "^2.4.1",
     "eslint": "^8.46.0",
     "eslint-plugin-import": "^2.28.0",
     "eslint-plugin-jsdoc": "^46.9.0",
     "eslint-plugin-n": "^16.3.1",
     "husky": "^8.0.3",
-    "ipull": "^1.2.1",
     "rimraf": "^5.0.1",
-    "semantic-release": "^22.0.8",
-    "ts-node": "^10.9.1",
+    "semantic-release": "^23.1.1",
     "tslib": "^2.6.1",
-    "typedoc": "^0.25.3",
-    "typedoc-plugin-markdown": "4.0.0-next.41",
-    "typedoc-plugin-mdn-links": "^3.1.5",
-    "typedoc-vitepress-theme": "^1.0.0-next.7",
+    "typedoc": "^0.25.13",
+    "typedoc-plugin-markdown": "^4.0.0-next.55",
+    "typedoc-plugin-mdn-links": "^3.1.24",
+    "typedoc-vitepress-theme": "1.0.0-next.10",
     "typescript": "^5.2.2",
-    "vitepress": "1.0.0-rc.22",
-    "vitest": "^0.34.6",
+    "vite-node": "^1.4.0",
+    "vitepress": "^1.1.4",
+    "vitest": "^1.4.0",
     "zx": "^7.2.3"
   },
   "dependencies": {
+    "@huggingface/jinja": "^0.2.2",
+    "async-retry": "^1.3.3",
+    "bytes": "^3.1.2",
     "chalk": "^5.3.0",
     "chmodrp": "^1.0.2",
-    "cli-progress": "^3.12.0",
-    "cmake-js": "^7.2.1",
+    "cmake-js": "^7.3.0",
     "cross-env": "^7.0.3",
     "cross-spawn": "^7.0.3",
     "env-var": "^7.3.1",
-    "fs-extra": "^11.1.1",
-    "lifecycle-utils": "^1.1.3",
+    "filenamify": "^6.0.0",
+    "fs-extra": "^11.2.0",
+    "ignore": "^5.3.1",
+    "ipull": "^3.1.1",
+    "is-unicode-supported": "^2.0.0",
+    "lifecycle-utils": "^1.4.1",
     "log-symbols": "^5.1.0",
+    "nanoid": "^5.0.7",
     "node-addon-api": "^7.0.0",
     "octokit": "^3.1.0",
     "ora": "^7.0.1",
+    "pretty-ms": "^9.0.0",
+    "proper-lockfile": "^4.1.2",
+    "semver": "^7.6.0",
     "simple-git": "^3.19.1",
-    "uuid": "^9.0.0",
+    "slice-ansi": "^7.1.0",
+    "stdout-update": "^4.0.1",
+    "strip-ansi": "^7.1.0",
+    "validate-npm-package-name": "^5.0.1",
     "which": "^4.0.0",
     "yargs": "^17.7.2"
   },