[4/n][torchtune integration] support lazy load model during inference (#620)

## What does this PR do?
In this PR, we refactor the meta reference inference logic to support 
- load the model during registering model instead of during spinning up
server
- support inference finetuned model checkpoint on top of native llama
model

## Why need these changes
To solve the existing pain points that 
- user cannot lazy load the model and hot switch the inference
checkpoint after spinning up the server
- this blocks us doing inference and eval on the same sever for a
finetuned checkpoint after post training
- user cannot do inference on a finetuned checkpoint on top of native
llama models

## Expect user experience change
- The inference model won't be loaded when spinning up server. Instead,
it will be loaded during register model. If user add the model as models
resource in run.yaml, it will be registered and loaded automatically
when starting server. There is an optional flag 'skip_initialize' in
model metadata to skip model loading during registration.
- There is an optional flag 'llama_model' in model metadata to identify
the base model of the Model class for validation and initialize model
arch. model identifier no longer needs to be a native llama model
- the default inference model name updates from
'meta-llama/Llama-3.2-3B-Instruct' to 'Llama3.2-3B-Instruct'
- It aligns with the checkpoint folder name after running 'llama model
download'
- It aligns with the descriptor name defined in llama-models SKU list
bf5b0c4fe7/models/datatypes.py (L95)


## test
run python llama_stack/scripts/distro_codegen.py


**run unit test**
- torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference"
--inference-model="Llama3.1-8B-Instruct"
./llama_stack/providers/tests/inference/test_text_inference.py
- torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference"
--inference-model="Llama3.1-8B-Instruct"
./llama_stack/providers/tests/inference/test_model_registration.py


**test post training experience**
on server side run: llama stack run
llama_stack/templates/experimental-post-training/run.yaml
server is spinning up without model loaded

<img width="812" alt="Screenshot 2024-12-17 at 1 24 50 PM"
src="https://github.com/user-attachments/assets/ce1f606b-3b6f-452f-b48e-b3761ffd90f3"
/>

on client side, run: llama-stack-client --endpoint
http://devgpu018.nha2.facebook.com:5000 models register
Llama3.2-3B-Instruct
register model successfully and the model is loaded 
<img width="1111" alt="Screenshot 2024-12-17 at 1 26 30 PM"
src="https://github.com/user-attachments/assets/56e02131-cf7d-4de5-8f63-fbdcb8c55c26"
/>


<img width="1541" alt="Screenshot 2024-12-17 at 1 26 09 PM"
src="https://github.com/user-attachments/assets/a83255a1-20f5-40a2-af51-55641410a115"
/>

if add "skip_initialize" in metadata, model is registered but isn't
loaded

on client side, run: llama-stack-client --endpoint
http://devgpu018.nha2.facebook.com:5000 inference chat-completion
--message "hello, what model are you?"

Inference the model succesfully
<img width="1121" alt="Screenshot 2024-12-17 at 1 27 33 PM"
src="https://github.com/user-attachments/assets/8e708545-3fe7-4a73-8754-1470fa5f1e75"
/>

**test inference experience**
run: llama stack run llama_stack/templates/meta-reference-gpu/run.yaml
model is loaded since the model is in resouce list in run.yaml 
<img width="1537" alt="Screenshot 2024-12-17 at 1 30 19 PM"
src="https://github.com/user-attachments/assets/5c8af817-66eb-43f8-bf4c-f5e24b0a12c6"
/>

on client side, run: llama-stack-client --endpoint
http://devgpu018.nha2.facebook.com:5000 inference chat-completion
--message "hello, what model are you?"
inference successfully 
<img width="1123" alt="Screenshot 2024-12-17 at 1 31 08 PM"
src="https://github.com/user-attachments/assets/471809aa-c65e-46dc-a37e-7094fb857f97"
/>



## inference on a finetuned model
**register a finetuned model that finetuned by post training api
(torchtune)**
- the model is registered and loaded successfully 
- the model is shown up in the model list 
<img width="974" alt="Screenshot 2024-12-18 at 3 56 33 PM"
src="https://github.com/user-attachments/assets/2994b4f5-4fa9-40c6-acc6-4b971479f3e2"
/>

**run inference**

<img width="977" alt="Screenshot 2024-12-18 at 3 57 59 PM"
src="https://github.com/user-attachments/assets/d117abbc-b2a0-41d8-a028-1a13128787b2"
/>

llama_stack/providers/inline/inference/meta_reference/config.py

@@ -7,19 +7,19 @@
 from typing import Any, Dict, Optional
 
 from llama_models.datatypes import *  # noqa: F403
-from llama_models.sku_list import resolve_model
 
 from llama_stack.apis.inference import *  # noqa: F401, F403
-from pydantic import BaseModel, Field, field_validator
+from pydantic import BaseModel, field_validator
 
 from llama_stack.providers.utils.inference import supported_inference_models
 
 
 class MetaReferenceInferenceConfig(BaseModel):
-    model: str = Field(
-        default="Llama3.2-3B-Instruct",
-        description="Model descriptor from `llama model list`",
-    )
+    # this is a placeholder to indicate inference model id
+    # the actual inference model id is dtermined by the moddel id in the request
+    # Note: you need to register the model before using it for inference
+    # models in the resouce list in the run.yaml config will be registered automatically
+    model: Optional[str] = None
     torch_seed: Optional[int] = None
     max_seq_len: int = 4096
     max_batch_size: int = 1
@@ -46,11 +46,6 @@ class MetaReferenceInferenceConfig(BaseModel):
             )
         return model
 
-    @property
-    def model_parallel_size(self) -> int:
-        resolved = resolve_model(self.model)
-        return resolved.pth_file_count
-
     @classmethod
     def sample_run_config(
         cls,