agentsculptor is an experimental AI-powered development agent designed to analyze, refactor, and extend Python projects automatically. It uses an OpenAI-like planner–executor loop on top of a vLLM backend, combining project context analysis, structured tool calls, and iterative refinement. It has only been tested with gpt-oss-120b via vLLM.

Deploy the Magistral-Small-2506 model using vLLM and Modal

Performant LLM inferencing on Kubernetes via vLLM

[KAIST CS632] Road damage detection using YOLOv8 on Xilinx FPGA, repair estimation with vLLM-Serve Phi-3.5 FAISS RAG, and data management via GS1 EPCISv2 and React dashboard

Load testing openai/gpt-oss-20b with vLLM and Docker

This Repository contains terraform configuration for vllm production-stack in the cloud managed K8s

Đây là mô hình OCR được tinh chỉnh từ Vintern1B (InternVL 1B) với 1 tỷ tham số. Mô hình có khả năng nhận diện văn bản trong nhiều ngữ cảnh khác nhau như chữ viết tay, chữ in, và văn bản trên các đối tượng thực tế.

Production-grade vLLM serving with an OpenAI-compatible API, per-request LoRA routing, KEDA autoscaling on Prometheus metrics, Grafana/OTel observability, and a benchmark comparing AWQ vs GPTQ vs GGUF.

[2024 Elice AI Hellothon Excellence Award (2nd Place)] Caregiver cognitive activity lesson guide creator and elderly interactive AI drawing diary service, Saem, Sam

GPU-Passthrough Enabled Apache Ray Clusters on Kubernetes (Kind) for POC and Testing