feat: Implement LlamaEagleSpeculator with

serialization support

  - Add LlamaEagleSpeculator model class
  - Implement model serialization/deserialization
  - Add torch as a project dependency
  - Include unit and integration tests
  - Fixes for serialization handling

  This introduces the core LlamaEagleSpeculator
  functionality with full serialization support

Author: rahul-tuli

pyproject.toml

@@ -46,6 +46,7 @@ dependencies = [
     "pydantic-settings>=2.0.0",
     "pyyaml>=6.0.0",
     "transformers",
+    "torch",
 ]
 
 [project.optional-dependencies]

src/speculators/models/__init__.py

@@ -1,9 +1,12 @@
 from .independent import IndependentSpeculatorConfig
+from .llama_eagle import LlamaEagleSpeculator, LlamaEagleSpeculatorConfig
 from .mlp import MLPSpeculatorConfig
 from .transformer import TransformerSpeculatorConfig
 
 __all__ = [
     "IndependentSpeculatorConfig",
+    "LlamaEagleSpeculator",
+    "LlamaEagleSpeculatorConfig",
     "MLPSpeculatorConfig",
     "TransformerSpeculatorConfig",
 ]