Pinned Loading

1. HPC-llm-bench HPC-llm-bench Public

   FSDP fine-tuning of Qwen2.5-7B on MMLU auxiliary_train with 3.6x inference throughput optimization (1.8x PagedAttention + continuous batching, 2.0x tensor parallelism) validated on 2-node H200 clus…

   Python

2. PrismBench PrismBench Public

   Benchmarking 9 data science agents across 6 evaluation dimensions (accuracy, code quality, explainability, speed, cost, robustness) with a preference-aware MCDM routing framework (WSM, TOPSIS, PROM…

   Jupyter Notebook

3. ConstellationAI-Multi-Agentic-RAG ConstellationAI-Multi-Agentic-RAG Public

   Production-ready multi-agent RAG system with LangGraph orchestration, real-time token optimization, GPU monitoring, semantic caching, and comprehensive performance analytics. Built for scale.

   Python 2

4. Multi-Robot-Coordination-Framework Multi-Robot-Coordination-Framework Public

   Multi-Robot Coordination Framework with distributed reinforcement learning achieving 92% convergence, <50ms allocation, and 99.9% availability Scalable autonomous robot fleet coordination using Q-l…

   Python 1

5. Production-LLM-Serving-Optimization-Framework Production-LLM-Serving-Optimization-Framework Public

   High-performance LLM inference platform with vLLM continuous batching achieving 12.3K+ req/sec, 42ms P50/178ms P99 latency, INT8/INT4 quantization (70% memory savings), tensor parallelism across 4 …

   Python

6. Transformer-based-Trajectory-Forecasting-system Transformer-based-Trajectory-Forecasting-system Public

   Transformer + Diffusion (DDPM) architecture for multi-agent pedestrian trajectory forecasting with temporal self-attention, social cross-attention, and DDIM sampling - evaluated on ETH/UCY benchmar…

   Python 2