v0.11.0: quantcpp CLI + progressive default + Llama-3.2-1B default

User feedback fixes:
- Added `quantcpp` CLI command (pip install → quantcpp "question")
- Default model: Llama-3.2-1B (SmolLM2-135M produced garbage)
- Progressive KV: ON by default everywhere

Usage:
  quantcpp "What is gravity?"     # one-shot
  quantcpp                         # interactive chat
  quantcpp -m my_model.gguf       # custom model

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: unamedkr

bindings/python/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "quantcpp"
-version = "0.10.1"
+version = "0.11.0"
 description = "Single-header LLM inference engine with KV cache compression (7× compression at fp32 parity)"
 readme = "README.md"
 license = { text = "Apache-2.0" }

bindings/python/quantcpp/__init__.py

@@ -15,7 +15,7 @@
     from importlib.metadata import version as _pkg_version
     __version__ = _pkg_version("quantcpp")
 except Exception:
-    __version__ = "0.10.1"  # fallback for editable / source-tree imports
+    __version__ = "0.11.0"  # fallback for editable / source-tree imports
 
 import os
 import sys