{"id":23934028,"url":"https://github.com/ajn313/ROME-LLM","last_synced_at":"2025-09-11T16:33:36.671Z","repository":{"id":250771061,"uuid":"834569857","full_name":"ajn313/ROME-LLM","owner":"ajn313","description":"Tools for Recurrent Optimization via Machine Editing and related benchmarks","archived":false,"fork":false,"pushed_at":"2024-08-03T22:05:24.000Z","size":951,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-08-04T22:45:47.508Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ajn313.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-07-27T17:07:29.000Z","updated_at":"2024-08-04T22:45:47.509Z","dependencies_parsed_at":"2024-07-30T02:27:21.794Z","dependency_job_id":"9ebe7498-3336-4a86-a14f-f75984a06ad5","html_url":"https://github.com/ajn313/ROME-LLM","commit_stats":null,"previous_names":["ajn313/rome-llm"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajn313%2FROME-LLM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajn313%2FROME-LLM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajn313%2FROME-LLM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ajn313%2FROME-LLM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ajn313","download_url":"https://codeload.github.com/ajn313/ROME-LLM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":232658737,"owners_count":18556991,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-01-06T00:30:03.504Z","updated_at":"2025-01-06T00:34:48.660Z","avatar_url":"https://github.com/ajn313.png","language":"Jupyter Notebook","funding_links":[],"categories":["Building"],"sub_categories":["Tools"],"readme":"# Recurrent Optimization via Machine Editing: ROME\nThe ROME tool automates hardware design with minimal human input. A large language model (LLM) is utilized to generate Verilog and fix errors in the resultant modules within a multi-stage design pipeline.\n\n![ROME-flowchart](https://github.com/ajn313/ROME-LLM/blob/main/supplements/flowchart.png)\n\nWe provide a [Colab notebook](https://github.com/ajn313/ROME-LLM/blob/main/ROME_demo.ipynb) which implements the tool. GPT-4 is used by default which will require an OpenAI API Key, but instructions to modify this will be provided.\n\nThe necessary inputs include the names of a series of simpler submodules which can be built up into a more complex target modules, as well as unit testbenches for each submodule. We include testbenches for a few hierarchical arcitectures, and more will continue to be added. \n\nGitHub still under construction. \n\n## Citation\n### Paper on arXiv:\n[Link](https://arxiv.org/abs/2407.18276)\n### BibTeX:\n```\n@misc{nakkab2024romebuiltsinglestep,\n      title={Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Design}, \n      author={Andre Nakkab and Sai Qian Zhang and Ramesh Karri and Siddharth Garg},\n      year={2024},\n      eprint={2407.18276},\n      archivePrefix={arXiv},\n      primaryClass={cs.AR},\n      url={https://arxiv.org/abs/2407.18276}, \n}\n```\n## Acknowledgements\nSpecial thanks to [Jason Blocklove](https://github.com/JBlocklove) for his work on error correction feedback loops for hardware design\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fajn313%2FROME-LLM","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fajn313%2FROME-LLM","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fajn313%2FROME-LLM/lists"}