node-llama-cpp 2.1.0 → 2.1.2

package/README.md

@@ -175,6 +175,23 @@ console.log("AI: " + a2);
 console.log(JSON.parse(a2));
 ```
 
+### Metal and CUDA support
+To load a version of `llama.cpp` that was compiled to use Metal or CUDA,
+you have to build it from source with the `--metal` or `--cuda` flag before running your code that imports `node-llama-cpp`.
+
+To do this, run this command inside of your project directory:
+```bash
+# For Metal support on macOS
+npx node-llama-cpp download --metal
+
+# For CUDA support
+npx node-llama-cpp download --cuda
+```
+
+> In order for `node-llama-cpp` to be able to build `llama.cpp` from source, make sure you have the required dependencies of `node-gyp` installed.
+> 
+> More info is available [here](https://github.com/nodejs/node-gyp#on-unix) (you don't have to install `node-gyp` itself, just the dependencies).
+
 ### CLI
 ```
 Usage: node-llama-cpp <command> [options]
@@ -206,6 +223,10 @@ Options:
                          ronment variable                               [string] [default: "latest"]
   -a, --arch             The architecture to compile llama.cpp for                          [string]
   -t, --nodeTarget       The Node.js version to compile llama.cpp for. Example: v18.0.0     [string]
+      --metal            Compile llama.cpp with Metal support. Can also be set via the NODE_LLAMA_CP
+                         P_METAL environment variable                     [boolean] [default: false]
+      --cuda             Compile llama.cpp with CUDA support. Can also be set via the NODE_LLAMA_CPP
+                         _CUDA environment variable                       [boolean] [default: false]
       --skipBuild, --sb  Skip building llama.cpp after downloading it     [boolean] [default: false]
   -v, --version          Show version number                                               [boolean]
 ```
@@ -220,6 +241,10 @@ Options:
   -h, --help        Show help                                                              [boolean]
   -a, --arch        The architecture to compile llama.cpp for                               [string]
   -t, --nodeTarget  The Node.js version to compile llama.cpp for. Example: v18.0.0          [string]
+      --metal       Compile llama.cpp with Metal support. Can also be set via the NODE_LLAMA_CPP_MET
+                    AL environment variable                               [boolean] [default: false]
+      --cuda        Compile llama.cpp with CUDA support. Can also be set via the NODE_LLAMA_CPP_CUDA
+                     environment variable                                 [boolean] [default: false]
   -v, --version     Show version number                                                    [boolean]
 ```
 

package/dist/index.d.ts

@@ -1,4 +1,4 @@
-import { LlamaGrammar } from "llamaEvaluator/LlamaGrammar.js";
+import { LlamaGrammar } from "./llamaEvaluator/LlamaGrammar.js";
 import { LlamaChatSession } from "./llamaEvaluator/LlamaChatSession.js";
 import { LlamaModel } from "./llamaEvaluator/LlamaModel.js";
 import { AbortError } from "./AbortError.js";

package/dist/index.js

@@ -1,4 +1,4 @@
-import { LlamaGrammar } from "llamaEvaluator/LlamaGrammar.js";
+import { LlamaGrammar } from "./llamaEvaluator/LlamaGrammar.js";
 import { LlamaChatSession } from "./llamaEvaluator/LlamaChatSession.js";
 import { LlamaModel } from "./llamaEvaluator/LlamaModel.js";
 import { AbortError } from "./AbortError.js";

package/dist/index.js.map

@@ -1 +1 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAC,YAAY,EAAC,MAAM,gCAAgC,CAAC;AAC5D,OAAO,EAAC,gBAAgB,EAAC,MAAM,sCAAsC,CAAC;AACtE,OAAO,EAAC,UAAU,EAAC,MAAM,gCAAgC,CAAC;AAC1D,OAAO,EAAC,UAAU,EAAC,MAAM,iBAAiB,CAAC;AAC3C,OAAO,EAAC,iBAAiB,EAAC,MAAM,wBAAwB,CAAC;AACzD,OAAO,EAAC,sBAAsB,EAAC,MAAM,0CAA0C,CAAC;AAChF,OAAO,EAAC,sBAAsB,EAAC,MAAM,0CAA0C,CAAC;AAChF,OAAO,EAAC,wBAAwB,EAAC,MAAM,4CAA4C,CAAC;AACpF,OAAO,EAAC,YAAY,EAAC,MAAM,kCAAkC,CAAC;AAC9D,OAAO,EAAC,mBAAmB,EAAC,MAAM,uCAAuC,CAAC;AAC1E,OAAO,EAAC,mBAAmB,EAAC,MAAM,0CAA0C,CAAC;AAK7E,OAAO,EACH,UAAU,EACV,YAAY,EACZ,YAAY,EACZ,gBAAgB,EAChB,UAAU,EACV,iBAAiB,EACjB,sBAAsB,EACtB,sBAAsB,EACtB,wBAAwB,EACxB,mBAAmB,EACnB,mBAAmB,EAEtB,CAAC"}
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAC,YAAY,EAAC,MAAM,kCAAkC,CAAC;AAC9D,OAAO,EAAC,gBAAgB,EAAC,MAAM,sCAAsC,CAAC;AACtE,OAAO,EAAC,UAAU,EAAC,MAAM,gCAAgC,CAAC;AAC1D,OAAO,EAAC,UAAU,EAAC,MAAM,iBAAiB,CAAC;AAC3C,OAAO,EAAC,iBAAiB,EAAC,MAAM,wBAAwB,CAAC;AACzD,OAAO,EAAC,sBAAsB,EAAC,MAAM,0CAA0C,CAAC;AAChF,OAAO,EAAC,sBAAsB,EAAC,MAAM,0CAA0C,CAAC;AAChF,OAAO,EAAC,wBAAwB,EAAC,MAAM,4CAA4C,CAAC;AACpF,OAAO,EAAC,YAAY,EAAC,MAAM,kCAAkC,CAAC;AAC9D,OAAO,EAAC,mBAAmB,EAAC,MAAM,uCAAuC,CAAC;AAC1E,OAAO,EAAC,mBAAmB,EAAC,MAAM,0CAA0C,CAAC;AAK7E,OAAO,EACH,UAAU,EACV,YAAY,EACZ,YAAY,EACZ,gBAAgB,EAChB,UAAU,EACV,iBAAiB,EACjB,sBAAsB,EACtB,sBAAsB,EACtB,wBAAwB,EACxB,mBAAmB,EACnB,mBAAmB,EAEtB,CAAC"}

package/llama/binariesGithubRelease.json

@@ -1,3 +1,3 @@
 {
-    "release": "b1107"
+    "release": "b1108"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "node-llama-cpp",
-  "version": "2.1.0",
+  "version": "2.1.2",
   "description": "node.js bindings for llama.cpp",
   "main": "dist/index.js",
   "type": "module",
@@ -70,6 +70,8 @@
     "prebuilt-binaries",
     "llm",
     "gguf",
+    "metal",
+    "cuda",
     "grammar",
     "json-grammar",
     "temperature",
@@ -111,7 +113,6 @@
     "zx": "^7.2.3"
   },
   "dependencies": {
-    "bytes": "^3.1.2",
     "chalk": "^5.3.0",
     "cli-progress": "^3.12.0",
     "cross-env": "^7.0.3",
@@ -119,9 +120,7 @@
     "env-var": "^7.3.1",
     "fs-extra": "^11.1.1",
     "node-addon-api": "^7.0.0",
-    "node-downloader-helper": "^2.1.9",
     "node-gyp": "^9.4.0",
-    "node-stream-zip": "^1.15.0",
     "octokit": "^3.1.0",
     "ora": "^7.0.1",
     "simple-git": "^3.19.1",