[init] v0.0.3 (#19)

v0.0.3 introduces these changes:
1. Introduces TokenizerInfo to uniformly handle various tokenizers, including huggingface tokenizer, tiktoken and mlc-llm tokenizer-cpp.
2. Introduces GrammarMatcherInitContext, an object that can be used to fast initialize multiple GrammarMatchers. A cache for GrammarMatcherInitContext called GrammarMatcherInitContextCache is introduces as well.
3. Introduces WebAssembly bindings for web uses.
4. Documents are refined for clearity.

python/xgrammar/version.py

@@ -15,4 +15,4 @@
 # specific language governing permissions and limitations
 # under the License.
 
-__version__ = "0.0.2"
+__version__ = "0.0.3"