Pinned Loading

1. Triton-Inference-Kernels Triton-Inference-Kernels Public

   Custom OpenAI Triton kernels for high-performance models inference. Accelerates models on NVIDIA GPUs by leveraging Triton's productivity and CUDA-level performance.

   Python

2. gpu-systems-playgrund gpu-systems-playgrund Public

   GPU Systems playground with cuda kernel expriments and performance profilling.

   Cuda 2

3. Veritas-AI-Tracking-Misinformation-with-Autonomous-Agents Veritas-AI-Tracking-Misinformation-with-Autonomous-Agents Public

   Veritas AI: An autonomous agent crew that scrapes prediction markets to create a RAG-powered chatbot for tracking misinformation and public belief in real-time.

   Python 1

4. AI-Action-Item-Extractor-Meeting-Dialogue-to-JSON AI-Action-Item-Extractor-Meeting-Dialogue-to-JSON Public

   🤖 AI Action Item Extractor 📝 — transforms meeting dialogues 🔄 into structured JSON tasks 📋; fine‑tunes and compares Mistral‑7B & Phi‑4 using QLoRA ⚡ for top‑tier performance and real‑world applicab…

   Python 1

5. Cuda-Attention-Optimization-journey Cuda-Attention-Optimization-journey Public

   How a 3x kernel speedup resulted in a tiny 6% overall gain, and the profiler that revealed why.

   Python 1

6. Hy-LoRA-A-Hybrid-SVD-LoRA-Strategy-for-Efficient-LLM-Adaptation Hy-LoRA-A-Hybrid-SVD-LoRA-Strategy-for-Efficient-LLM-Adaptation Public

   Achieve >60% LLM compression with near-baseline perplexity using a novel "Compress-then-Adapt" strategy.

   Python 1