[Hardware][Neuron] Refactor neuron support (#3471)

examples/offline_inference_neuron.py

@@ -12,7 +12,7 @@ sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
 
 # Create an LLM.
 llm = LLM(
-    model="openlm-research/open_llama_3b",
+    model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
     max_num_seqs=8,
     # The max_model_len and block_size arguments are required to be same as
     # max sequence length when targeting neuron device.
@@ -24,7 +24,8 @@ llm = LLM(
     # The device can be automatically detected when AWS Neuron SDK is installed.
     # The device argument can be either unspecified for automated detection,
     # or explicitly assigned.
-    device="neuron")
+    device="neuron",
+    tensor_parallel_size=2)
 # Generate texts from the prompts. The output is a list of RequestOutput objects
 # that contain the prompt, generated text, and other information.
 outputs = llm.generate(prompts, sampling_params)