update code

.gitignore

+experiments/*
+results/*
+tb_logger/*
+wandb/*
+tmp/*
+modify_model.py
+hat/version.py
+
+*.DS_Store
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

README.md

+# llm-compiler
+ LLM Compiler: Specializing Code Llama for compiler optimization
+## 论文
+[Meta Large Language Model Compiler: Foundation Models of Compiler Optimization](https://scontent-sjc3-1.xx.fbcdn.net/v/t39.2365-6/448997590_1496256481254967_2304975057370160015_n.pdf?_nc_cat=106&ccb=1-7&_nc_sid=3c67a6&_nc_ohc=9EBooh-SwxIQ7kNvgHFCHvh&_nc_ht=scontent-sjc3-1.xx&oh=00_AYAZqBNdevNLWa6cuTIuvxhG31CBJRu61vyjmbSLiV9sFg&oe=669C1E0D)
+
+## 模型结构
+
+LLM编译器模型是通过在两个阶段对5460亿个编译器中心数据token进行训练，从Code Llama专业化的。在第一阶段，模型主要对未标记的编译器IR和汇编代码进行训练。在下一阶段，模型经过指令微调，以预测优化的输出和效果。然后，LLM编译器FTD模型在下游标志调整和反汇编任务数据集的1640亿个token上进一步微调，总共进行了7100亿个训练token。
+<div align=center>
+    <img src="./assets/model_framework.png"/>
+</div>
+
+## 算法原理
+
+使用GQA模块能够带来更好的速度，使用GQA的head数量不同则会带来速度和性能平衡转换
+使用了RoPE位置旋转编码来替代Embedding编码，使得模型获得更好的外推性。
+
+<div align=center>
+    <img src="./assets/model.png"/>
+</div>
+
+
+## 环境配置
+-v 路径、docker_name和imageID根据实际情况修改
+
+### Docker（方法一）
+
+```bash
+docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk24.04-py310
+docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=80G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
+
+cd /your_code_path/llm-compiler_pytorch
+pip install -r requirements.txt
+pip install -U huggingface_hub hf_transfer
+export HF_ENDPOINT=https://hf-mirror.com
+```
+
+### Dockerfile（方法二）
+
+```bash
+cd docker
+docker build --no-cache -t llm-compiler:latest .
+docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=80G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
+
+cd /your_code_path/llm-compiler_pytorch
+pip install -r requirements.txt
+pip install -U huggingface_hub hf_transfer
+export HF_ENDPOINT=https://hf-mirror.com
+
+```
+
+### Anaconda（方法三）
+关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。
+```
+DTK驱动: dtk24.04
+python: python3.10
+torch: 2.1.0
+```
+`Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应`
+
+其它非深度学习库安装方式如下：
+```bash
+pip install -r requirements.txt
+pip install -U huggingface_hub hf_transfer
+export HF_ENDPOINT=https://hf-mirror.com
+```
+
+## 数据集
+暂无
+
+## 训练
+暂无
+
+## 推理
+基于Huggingface's Transformers进行推理.<br>
+模型下载后 默认需存放至weights文件夹中<br>
+也可自行更改 inference.py文件中的 model_name 参数<br>
+```python
+HIP_VISIBLE_DEVICES=0 python inference.py
+```
+## Result
+prompt：%3 = alloca i32, align 4.<br>
+<div align=center>
+    <img src="./assets/result.png"/>
+</div>
+
+### 精度
+暂无
+
+## 应用场景
+### 算法类别
+代码生成
+
+### 热点应用行业
+制造,能源,教育
+
+## 预训练权重
+
+- 模型权重快速下载中心:
+  - [SCNet AIModels](http://113.200.138.88:18080/aimodels)
+- 模型快速通道下载地址：
+  - [数据集快速下载地址](http://113.200.138.88:18080/aimodels?filter=llm-compiler)
+- 官方下载通道
+  - [llm-compiler-7b](https://huggingface.co/facebook/llm-compiler-7b)
+
+
+模型目录结构如下：
+```bash
+└── llm-compiler-7b
+    ├── config.json
+    ├── generation_config.json
+    ├── LICENSE.pdf
+    ├── llm_compiler_demo.py
+    ├── pytorch_model-00001-of-00003.bin
+    ├── pytorch_model-00002-of-00003.bin
+    ├── pytorch_model-00003-of-00003.bin
+    ├── pytorch_model.bin.index.json
+    ├── readme
+    │   ├── autotune.png
+    │   ├── disassemble.png
+    │   ├── emulate.png
+    │   └── training.png
+    ├── README.md
+    ├── special_tokens_map.json
+    ├── tokenizer_config.json
+    ├── tokenizer.json
+    └── tokenizer.model
+```
+
+## 源码仓库及问题反馈
+- https://developer.hpccube.com/codes/modelzoo/llm-compiler_pytorch
+
+## 参考资料
+- https://huggingface.co/facebook/llm-compiler-7b/blob/main/llm_compiler_demo.py
+- https://huggingface.co/facebook/llm-compiler-7b

docker/Dockerfile

+FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk24.04-py310
\ No newline at end of file

inference.py

+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "facebook/llm-compiler-7b"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+sequences = pipeline(
+    '%3 = alloca i32, align 4',
+    do_sample=True,
+    top_k=10,
+    temperature=0.1,
+    top_p=0.95,
+    num_return_sequences=1,
+    eos_token_id=tokenizer.eos_token_id,
+    max_length=200,
+)
+for seq in sequences:
+    print(f"Result: {seq['generated_text']}")
\ No newline at end of file

model.properties

+# 模型唯一标识
+modelCode=801
+# 模型名称
+modelName=llm-compiler_pytorch
+# 模型描述
+modelDescription=llm-compiler是Meta大型语言模型编译器 (LLM Compiler)，这是一套强大的、公开可用的、预先训练的模型，专为代码优化任务而设计。
+# 应用场景
+appScenario=推理,训练,代码生成,制造,能源,教育
+# 框架类型
+frameType=pytorch

requirements.txt

+#torch>=2.0
+#tokenizers>=0.14.0
+#transformers==4.35.0
+#accelerate
+#deepspeed==0.12.2
+sympy==1.12
+pebble 
+timeout-decorator 
+accelerate
+attrdict
+tqdm
+datasets
+tensorboardX