[Version] Bump version to 0.2.58, support embedding (#539)

### Change

- Supports embedding via OpenAI API `engine.embeddings.create()`:
  - #538
- Currently, only `snowflake-arctic-embed-s` and
`snowflake-arctic-embed-m` are supported. We add the following models to
the prebuilt model list:
  - `snowflake-arctic-embed-m-q0f32-MLC-b32`
  - `snowflake-arctic-embed-m-q0f32-MLC-b4`
  - `snowflake-arctic-embed-s-q0f32-MLC-b32`
  - `snowflake-arctic-embed-s-q0f32-MLC-b4`
- `b32` means the model is compiled to support a maximum batch size of
32. If an input with more than 32 entries are provided, we will call
multiple `forward()` (e.g. if input has 67 entries, we forward 3 times).
The larger the maximum batch size, the more memory it takes to load the
model. See `ModelRecord.vram_required_MB` in `config.ts` for specifics.


### TVMjs
Still compiled at
apache/tvm@1fcb620,
no change

examples/abort-reload/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/cache-usage/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/chrome-extension-webgpu-service-worker/package.json

@@ -17,7 +17,7 @@
     "url": "^0.11.1"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57",
+    "@mlc-ai/web-llm": "^0.2.58",
     "progressbar.js": "^1.1.0"
   }
 }

examples/chrome-extension/package.json

@@ -17,7 +17,7 @@
     "url": "^0.11.1"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57",
+    "@mlc-ai/web-llm": "^0.2.58",
     "progressbar.js": "^1.1.0"
   }
 }

examples/embeddings/package.json

@@ -15,7 +15,7 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "file:../..",
+    "@mlc-ai/web-llm": "^0.2.58",
     "langchain": "0.2.15"
   }
 }

examples/function-calling/function-calling-manual/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/function-calling/function-calling-openai/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/get-started-web-worker/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/get-started/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/json-mode/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/json-schema/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/logit-processor/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/multi-round-chat/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/next-simple-chat/package.json

@@ -9,7 +9,7 @@
     "lint": "next lint"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57",
+    "@mlc-ai/web-llm": "^0.2.58",
     "@types/node": "20.3.3",
     "@types/react": "18.2.14",
     "@types/react-dom": "18.2.6",

examples/seed-to-reproduce/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/service-worker/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/simple-chat-ts/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/streaming/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

examples/text-completion/package.json

@@ -15,6 +15,6 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57"
+    "@mlc-ai/web-llm": "^0.2.58"
   }
 }

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mlc-ai/web-llm",
-  "version": "0.2.57",
+  "version": "0.2.58",
   "description": "Hardware accelerated language model chats on browsers",
   "main": "lib/index.js",
   "types": "lib/index.d.ts",

utils/vram_requirements/package.json

@@ -19,7 +19,7 @@
     "url": "^0.11.3"
   },
   "dependencies": {
-    "@mlc-ai/web-llm": "^0.2.57",
+    "@mlc-ai/web-llm": "^0.2.58",
     "tvmjs": "file:./../../tvm_home/web"
   }
 }