Add Qwen2 Support

[jlonge4]

Issue #, if available:
aws-neuron/neuron-workshops#7

Description of changes:
This PR adds support for Qwen2 Models

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[FThompsonAWS]

Thank you for your contribution! We are defining our process to review/accept contributions and will get back to you soon.

[jlonge4]

Logit Validation Benchmark Code:

!inference_demo \
    --model-type qwen2 \
    --task-type causal-lm \
    run \
    --model-path /home/ubuntu/model_hf_qwen/qwen2 \
    --compiled-model-path /home/ubuntu/traced_model_qwen/qwen2/logit \
    --torch-dtype bfloat16 \
    --tp-degree 8 \
    --batch-size 1 \
    --max-context-length 16 \
    --seq-len 32 \
    --top-k 1 \
    --pad-token-id 151645 \
    --prompt "To be, or not to be" \
    --check-accuracy-mode logit-matching \
    --benchmark

Results:

Expected Output:  [", that is the question. Whether 'tis nobler in the mind to suffer the slings and arrows of outrageous fortune"] tensor([[   11,   429,   374,   279,  3405,    13, 13139,   364,    83,   285,
         13049,  1536,   304,   279,  3971,   311,  7676,   279,  1739,   819,
           323, 36957,   315, 54488, 32315]])
Expected Logits Shape:  torch.Size([25, 1, 152064])
Actual Output:  [", that is the question. Whether 'tis nobler in the mind to suffer the slings and arrows of outrageous fortune"] tensor([[   11,   429,   374,   279,  3405,    13, 13139,   364,    83,   285,
         13049,  1536,   304,   279,  3971,   311,  7676,   279,  1739,   819,
           323, 36957,   315, 54488, 32315]])
Actual Logits Shape:  torch.Size([25, 1, 152064])
Passed logits validation!

Generating outputs...
Prompts: ['To be, or not to be']
Generated outputs:
Output 0: To be, or not to be, that is the question. Whether 'tis nobler in the mind to suffer the slings and arrows of outrageous fortune
Benchmark completed and its result is as following
{
    "e2e_model": {
        "latency_ms_p50": 556.2845468521118,
        "latency_ms_p90": 556.8541049957275,
        "latency_ms_p95": 556.9546341896057,
        "latency_ms_p99": 557.6868557929993,
        "latency_ms_p100": 557.8699111938477,
        "latency_ms_avg": 555.8973550796509,
        "throughput": 57.56458401464229
    },
    "context_encoding_model": {
        "latency_ms_p50": 41.66257381439209,
        "latency_ms_p90": 41.74163341522217,
        "latency_ms_p95": 41.74485206604004,
        "latency_ms_p99": 41.75789833068848,
        "latency_ms_p100": 41.761159896850586,
        "latency_ms_avg": 41.67191982269287,
        "throughput": 383.9515930170089
    },
    "token_generation_model": {
        "latency_ms_p50": 33.31899642944336,
        "latency_ms_p90": 33.50291252136231,
        "latency_ms_p95": 33.71169567108154,
        "latency_ms_p99": 33.97499084472656,
        "latency_ms_p100": 34.55924987792969,
        "latency_ms_avg": 33.36369752883911,
        "throughput": 31.970876901298336
    }
}