Update code and docs to latest version (#4)

* Update README and add docs

* Update to latest version of code

* Run formatter

* init

* Fix pylint warnings

* Make run command in readme run successfully, add profiling data

* Remove scripts and experiments

* Fix batch.completed conflicting definitions

* Use github python gitgignore as base

* Remove experiments folder

* Remove constants from execution time predictor

.gitignore

@@ -1,17 +1,165 @@
-env
-env_2
-env_pypy
-cache
-cache_lr
-env_cpython
-.vscode
-# data
-simulator_output
-wandb
-
-# python files
+# Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
 *$py.class
-.ipynb_checkpoints
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Custom
+simulator_output*
+wandb
+.cache

README.md

@@ -1,30 +1,37 @@
-# LLM Inference Simulator
-
-## Overview
-
-LLM inference system simulator.
+# VIDUR: LLM Inference Simulator
 
 ## Setup
 
-To run the simulator, create a conda environment with the given dependency file.
+### Using `mamba`
 
-```
-conda env create -p ./env -f ./environment.yml
+To run the simulator, create a mamba environment with the given dependency file.
+
+```sh
+mamba env create -p ./env -f ./environment.yml
 ```
 
-## Formatting Code
+### Using `venv`
 
-To run the code formatters execute the following command,
+1. Ensure that you have python 3.10 installed on your system. Refer <https://www.bitecode.dev/p/installing-python-the-bare-minimum>
+2. `cd` into the repository root
+3. Create a virtual environment using `venv` module using `python3.10 -m venv .venv`
+4. Activate the virtual environment using `source .venv/bin/activate`
+5. Install the dependencies using `python -m pip install -r requirements.txt`
+6. Run `deactivate` to deactivate the virtual environment
 
-```
-make format
+### Using `conda` (Least recommended)
+
+To run the simulator, create a conda environment with the given dependency file.
+
+```sh
+conda env create -p ./env -f ./environment.yml
 ```
 
-## Setting up wandb
+## Setting up wandb (Optional)
 
-First, setup your account on https://microsoft-research.wandb.io/, obtain the api key and then run the following command,
+First, setup your account on <https://microsoft-research.wandb.io/>, obtain the api key and then run the following command,
 
-```
+```sh
 wandb login --host https://microsoft-research.wandb.io
 ```
 
@@ -34,12 +41,54 @@ If you wish to skip wandb setup, simply comment out `wandb_project` and `wandb_g
 
 To run the simulator, simply execute the following command from the repository root,
 
-```
+```sh
 python -m simulator.main
 ```
 
+or a big example with all the parameters,
+
+```sh
+python -m simulator.main \
+--replica_model_name codellama/CodeLlama-34b-Instruct-hf \
+--replica_num_layers 48 \
+--replica_num_q_heads 64 \
+--replica_num_kv_heads 8 \
+--replica_embedding_dim 8192 \
+--replica_mlp_hidden_dim 22016 \
+--replica_vocab_size 32768 \
+--replica_use_gated_mlp \
+--replica_fp16_tflops 312 \
+--replica_total_memory_gb 80 \
+--sklearn_execution_time_predictor_compute_input_file ./data/profiling/a100/mlp.csv \
+--sklearn_execution_time_predictor_attention_input_file ./data/profiling/a100/mixed_attention.csv \
+--sklearn_execution_time_predictor_all_reduce_input_file ./data/profiling/a100/all_reduce.csv \
+--sklearn_execution_time_predictor_send_recv_input_file ./data/profiling/a100/p2p_intra_node.csv \
+--sklearn_execution_time_predictor_cpu_overhead_input_file ./data/profiling/a100/cpu_overheads.csv \
+--cluster_num_replicas 1 \
+--replica_num_tensor_parallel_workers 1 \
+--request_generator_provider synthetic \
+--synthetic_request_generator_length_provider trace \
+--trace_request_length_generator_trace_file ./data/processed_traces/cnn_dailymail_stats_llama2_tokenizer.csv \
+--synthetic_request_generator_interval_provider poisson \
+--poisson_request_interval_generator_qps 0.75 \
+--synthetic_request_generator_num_requests 256 \
+--replica_scheduler_provider vllm \
+--replica_scheduler_batch_size_cap 128
+```
+
+The simulator supports a plethora of parameters for the simulation description of which can be found [here](docs/simulator_params.md).
+
 The metrics will be logged to wandb directly and copy will be stored in `simulator_output` directory along with the chrome trace. Description of all the logged metrics can be found [here](docs/simulator_metrics.md).
 
+## Formatting Code
+
+To run the code formatters execute the following command,
+
+```sh
+make format
+```
+
+
 ## Contributing
 
 This project welcomes contributions and suggestions.  Most contributions require you to agree to a