[ChatModule] Add GenerationConfig and set up unit tests (mlc-ai#298)

This PR adds `GenerationConfig`, which allows per-generation configs.
See `get-started.ts` for its example usage:

```typescript
let genConfig: webllm.GenerationConfig = {
  presence_penalty: 0.5,
  frequency_penalty: 0.5,
  max_gen_len: 20,
  // stop: ["is", "Canada"]  // for demonstration purpose
}

const prompt0 = "What is the capital of Canada?";
const reply0 = await chat.generate(prompt0, generateProgressCallback, 1, genConfig);
```

In addition to the existing fields in `mlc-chat-config.json`, we also
support OpenAI-like fields `frequency_penalty`, `presence_penalty`, and
`stop` to prepare for the incoming OpenAI-like APIs.

This PR also sets up unit tests; use `npm test` to run tests. However,
some work needs to be done to support end-to-end testing (e.g. accessing
WebGPU in a test environment).

All prebuilt WASMs are updated correspondingly:
mlc-ai/binary-mlc-llm-libs#90 as we introduced a
new API in tvmjs's `runtime.ts` via
apache/tvm#16504.

Note that the update of Llama WASMs is breaking in the sense that users
will have to update their WebLLM npm.

Author: CharlieFRuan

examples/get-started-rest/package.json

@@ -1,5 +1,5 @@
 {
-    "name": "get-started",
+    "name": "get-started-rest",
     "version": "0.1.0",
     "private": true,
     "scripts": {

examples/get-started/src/get_started.ts

@@ -33,7 +33,7 @@ async function main() {
     ]
   }
   const selectedModel = "Llama-2-7b-chat-hf-q4f32_1"
-  // const selectedModel = "Mistral-7B-Instruct-v0.1-q4f16_1"
+  // const selectedModel = "Mistral-7B-Instruct-v0.2-q4f16_1"
   await chat.reload(selectedModel, undefined, myAppConfig);
 
   // Option 2: If we do not specify appConfig, we use `prebuiltAppConfig` defined in `config.ts`
@@ -43,14 +43,24 @@ async function main() {
     setLabel("generate-label", message);
   };
 
+  // Per-generation configuration
+  let genConfig: webllm.GenerationConfig = {
+    presence_penalty: 0.5,
+    frequency_penalty: 0.5,
+    // stop: ["is", "Canada"]  // for demonstration purpose
+  }
+
   const prompt0 = "What is the capital of Canada?";
   setLabel("prompt-label", prompt0);
-  const reply0 = await chat.generate(prompt0, generateProgressCallback);
+  const reply0 = await chat.generate(prompt0, generateProgressCallback, 1, genConfig);
   console.log(reply0);
 
+  genConfig = {
+    max_gen_len: 20,
+  }
   const prompt1 = "Can you write a poem about it?";
   setLabel("prompt-label", prompt1);
-  const reply1 = await chat.generate(prompt1, generateProgressCallback);
+  const reply1 = await chat.generate(prompt1, generateProgressCallback, 1, genConfig);
   console.log(reply1);
 
   console.log(await chat.runtimeStatsText());

jest.config.cjs

@@ -0,0 +1,4 @@
+module.exports = {
+    preset: "ts-jest",
+    testEnvironment: "node",
+};