🤓 Latest Submissions
Merge Conflict Resolver using IBM BOB
Merge conflicts are tedious: developers must stop, read both sides, and manually reconcile them before continuing. Our tool automates that first pass. A CLI engine scans a repo for conflicts and sends each one to IBM Bob Shell for a proposed resolution, returning structured tickets with a confidence score and reasoning. High-confidence fixes are auto-resolved; uncertain ones are flagged for review. A web dashboard sits on top: developers and team leads click "Run" to scan a repo, see tickets by status, compare both original sides against the suggested fix, and approve or reject with one click, which rewrites the source file directly. What makes it unique is pairing an LLM-driven CLI with a lightweight ticketing UI, plus GitHub-connected repo access and Slack alerts, so teams learn about conflicts the moment they're created instead of mid-merge, cutting resolution time while keeping a human in the loop for anything ambiguous.
27 Sep 2026
.png&w=828&q=75)
Qwen 2.5 VL OCR trained on ROCm
The AMD AI Academy Optical Character Recognition (OCR) challenge focuses on building an end-to-end vision pipeline capable of extracting text from complex road scene images under real-world conditions. Designed for autonomous driving and surveillance applications, the system recognizes text across diverse categories: US license plates (extracting registration numbers while filtering out state banners and slogans), Chinese license plates (retaining province prefixes), speed limit postings, advisory speed plaques, stop signs, and multi-line work zone signage. The pipeline is built to maintain high accuracy despite adverse environmental factors like glare, motion blur, sensor noise, low lighting, and severe perspective angles. Architecturally, the application leverages advanced open-source Vision-Language Models (such as Qwen2-VL) running on AMD ROCm GPU acceleration. To strictly meet evaluation constraints—including a 30-second per-image inference limit and a total 10-minute run budget—the application uses a persistent background daemon (FastAPI/vLLM). Model weights are loaded into VRAM once at container boot, allowing the CLI entrypoint script (app/app.py) to execute inference calls with sub-second latency via local HTTP requests. The entire application is packaged inside a Docker container built strictly on the mandated base image (rocm/pytorch:rocm10.0_ubuntu26.04_py3.14_pytorch_release_2.13.0), keeping the uncompressed image under 60 GiB and peak GPU VRAM usage between 1 GiB and 48 GiB. Custom post-processing logic enforces domain-specific rules before generating normalized output JSON files for automated scoring
1 Dec 2026
