TP/quantization/weight loading refactor part 2 - Refactor quantized linear logic and extend quantization support to all models (#1622)

Refactor the tensor parallelism, quantization, and weight-loading codes.

Summary of the new features enabled by this PR:
- **All models** are able to be quantized with AWQ and SqueezeLLM, and [soon GPTQ](https://github.com/vllm-project/vllm/pull/1580).
- Model loading code became much simpler.
- Support model parallelism for all MQA/GQA models when the number of key/value heads is smaller than the tensor parallel size.

vllm/model_executor/layers/quantization/__init__.py

@@ -0,0 +1,22 @@
+from typing import Type
+
+from vllm.model_executor.layers.quantization.awq import AWQConfig
+from vllm.model_executor.layers.quantization.squeezellm import SqueezeLLMConfig
+from vllm.model_executor.layers.quantization.base_config import QuantizationConfig
+
+_QUANTIZATION_CONFIG_REGISTRY = {
+    "awq": AWQConfig,
+    "squeezellm": SqueezeLLMConfig,
+}
+
+
+def get_quantization_config(quantization: str) -> Type[QuantizationConfig]:
+    if quantization not in _QUANTIZATION_CONFIG_REGISTRY:
+        raise ValueError(f"Invalid quantization method: {quantization}")
+    return _QUANTIZATION_CONFIG_REGISTRY[quantization]
+
+
+__all__ = [
+    "QuantizationConfig",
+    "get_quantization_config",
+]