Add support of Qwen models (7b, 14b, 72b) to DeepSpeed-FastGen

[ZonePG]

This PR adds support for Qwen models 7b, 14b and 72b.

Test Code

for mii pipeline:

from mii import pipeline
pipe = pipeline("Qwen/Qwen-7B-Chat")
pipe.tokenizer.tokenizer.eos_token_id = 151643
output = pipe(["DeepSpeed is"], max_new_tokens=128, do_sample=False)
print(output)

for huggingface:

from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, fp16=True).eval()
inputs = tokenizer('DeepSpeed is', return_tensors='pt')
inputs = inputs.to(model.device)
pred = model.generate(**inputs, max_new_tokens=128, do_sample=False, repetition_penalty=1.0)
test = tokenizer.decode(pred.cpu()[0], skip_special_tokens=False)
print(test)

Qwen 7B

Huggingface output with prompt "DeepSpeed is":

 a high-performance, low-latency database management system designed for real-time analytics and machine learning applications. It is built on top of Apache Arrow, a columnar in-memory data format, and is optimized for processing large volumes of data in parallel.\n\nDeepSpeed offers several key features that make it well-suited for real-time analytics and machine learning applications:\n\n1. High Performance: DeepSpeed is designed to deliver high performance by leveraging parallel processing and optimized data structures. It can process large volumes of data in real-time, making it ideal for applications that require real-time analytics.\n\n2. Low Latency: DeepSpeed is designed to minimize latency by

DeepSpeed-FastGen output with prompt "DeepSpeed is":

 a high-performance, low-latency database management system designed for real-time analytics and machine learning applications. It is built on top of Apache Arrow, a columnar in-memory data format, and is optimized for processing large volumes of data in parallel.\n\nDeepSpeed offers several key features that make it well-suited for real-time analytics and machine learning applications:\n\n1. High Performance: DeepSpeed is designed to deliver high performance by leveraging parallel processing and optimized data structures. It can process large volumes of data in real-time, making it ideal for applications that require real-time analytics.\n\n2. Low Latency: DeepSpeed is designed to minimize latency by

Qwen 72B

Huggingface output with prompt "DeepSpeed is":

是一个开源的深度学习优化库，它提供了多种优化技术，包括模型并行、数据并行、混合并行、ZeRO内存优化等。它可以帮助用户在大规模GPU集群上训练深度学习模型，提高训练速度，减少内存使用。\n在Deepspeed中，模型并行是一种将模型的不同部分分配到不同的GPU上的技术。这样可以处理模型太大，无法放在一个GPU上的问题。数据并行是将数据集分成多个部分，每个部分在不同的GPU上进行训练。混合并行则是结合了模型并行和数据并行，以更有效地利用GPU资源

DeepSpeed-FastGen output with prompt "DeepSpeed is" with 8-way sharding:

是一个开源的深度学习优化库，它提供了多种优化技术，包括模型并行、数据并行、混合并行、ZeRO内存优化等。它可以帮助用户在大规模GPU集群上训练深度学习模型，提高训练速度，减少内存使用。\n在Deepspeed中，模型并行是一种将模型的不同部分分配到不同的GPU上的技术。这样可以处理模型太大，无法放在一个GPU上的问题。数据并行是将数据集分成多个部分，每个部分在不同的GPU上进行训练。混合并行则是结合了模型并行和数据并行，以更有效地利用GPU资源

[ZonePG]

@microsoft-github-policy-service agree

[mrwyattii]

@ZonePG thank you for this contribution! Could you please run the pre-commit and commit any modified files? pre-commit run --all-files

[ZonePG]

@mrwyattii pre-commit checks have been run and all modified files have been committed. Thanks!