[3/N] rs/vllm quantization - Adding models to non-uniform refactor

[robertgshaw2-redhat]

Since we changes the LinearMethod interface to require layer_name, we need to update each model.py to plumb this information through the models. We need to do this, because we need to pass the layer_name to LinearMethodBase.create_weights, such that we have have non-uniform quantization / compression (as we need to be able to consult the quantization config to determine what the weights / format should look like and we use the layer name to decide this

So far, have updated:

• llama
• gemma
• phi-2
• gpt2
• starcoder2
• qwen2
• deepseek and deepseekMoE
• baichuan

To test:

python3 examples/simple_test.py --help

To Update:

• Pass layer_name to QKVParallelLinear, MergedColumnParallelLinear, ColumnParallelLinear, RowParallelLinear by plumbing parent_name through from Model --> DecoderLayer --> MLP / SelfAttention --> Layer
• Updated weight_loader with linear_method.maybe_update_name