{"id":30481810,"url":"https://github.com/maneeshsit/pcie","last_synced_at":"2025-08-24T14:27:16.772Z","repository":{"id":276726792,"uuid":"930095941","full_name":"maneeshsit/PCIe","owner":"maneeshsit","description":"Modify run:ai and other FOSS projects code for use with PCIe card-based AI accelerators for both inference and training","archived":false,"fork":false,"pushed_at":"2025-08-11T13:30:13.000Z","size":50,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-11T15:22:26.062Z","etag":null,"topics":["cuda","cxl","cxl-mem","distro","exo","k3s","k8s","kestra","llamacpp","llm-d","mpi4py","mpio","onnxoptimizer","opentelemetry-ebpf-profiler","paxos-cluster","pcie","photonics-computing","runai","visualize","vllm"],"latest_commit_sha":null,"homepage":"https://medium.com/@maneeshsharma_68969/comparing-performance-of-ai-ml-hardware-a0d18cf657a0","language":"Python","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/maneeshsit.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,"zenodo":null}},"created_at":"2025-02-10T04:03:53.000Z","updated_at":"2025-08-11T13:30:16.000Z","dependencies_parsed_at":"2025-08-11T15:12:26.604Z","dependency_job_id":"0516a854-6f78-42d3-bc4f-07aba1b89c49","html_url":"https://github.com/maneeshsit/PCIe","commit_stats":null,"previous_names":["maneeshsit/pcie"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/maneeshsit/PCIe","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maneeshsit%2FPCIe","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maneeshsit%2FPCIe/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maneeshsit%2FPCIe/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maneeshsit%2FPCIe/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/maneeshsit","download_url":"https://codeload.github.com/maneeshsit/PCIe/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/maneeshsit%2FPCIe/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271886749,"owners_count":24838946,"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","status":"online","status_checked_at":"2025-08-24T02:00:11.135Z","response_time":111,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["cuda","cxl","cxl-mem","distro","exo","k3s","k8s","kestra","llamacpp","llm-d","mpi4py","mpio","onnxoptimizer","opentelemetry-ebpf-profiler","paxos-cluster","pcie","photonics-computing","runai","visualize","vllm"],"created_at":"2025-08-24T14:27:15.382Z","updated_at":"2025-08-24T14:27:16.750Z","avatar_url":"https://github.com/maneeshsit.png","language":"Python","readme":"# PCIe\nModify run.ai code for using a PCIe-based AI accelerator (such as a GPU, FPGA, or ASIC like NVIDIA, Xilinx, or Intel accelerators) for both inference and training\n1. Set Up the PCIe AI Accelerator\nInstall the required drivers and SDKs for your PCIe accelerator. For example:\nNVIDIA GPUs: Install CUDA and cuDNN.\nIntel accelerators: Install OpenVINO Toolkit.\nXilinx FPGAs: Install Vitis AI runtime.\nEnsure the PCIe device is visible via tools like lspci (Linux) or equivalent commands.\n\n2. Modify Training Code\nUse the appropriate deep learning framework and ensure device targeting is set to the PCIe accelerator. Examples:\n\n3. and 4.  code files\n\n5. Use Accelerator-Specific Optimizations\nFor NVIDIA GPUs: Use TensorRT for inference optimization.\nFor Intel FPGAs: Use OpenVINO's optimized inference engine.\nFor Xilinx FPGAs: Use Vitis AI tools for quantization and deployment.\n\n\n6. Monitor and Debug\nUse monitoring tools to ensure efficient usage of the PCIe accelerator:\nNVIDIA: nvidia-smi\nIntel: OpenVINO Benchmark Tool\nXilinx: Vitis AI Profiler\n\n# AI hardware accelerator-agnostic AI Platform Factory\n![AI Platform Factory](https://github.com/user-attachments/assets/423d5a85-9c8b-44dc-b47a-41ddce3c48d7)\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaneeshsit%2Fpcie","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmaneeshsit%2Fpcie","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmaneeshsit%2Fpcie/lists"}