Pinned Loading

1. MedWise MedWise Public

   SF Hacks 2x Category Winner

   TypeScript

2. viewlingo viewlingo Public

   Forked from kevinlinxc/viewlingo

   YCombinator x Mentra Hackathon Winner

   TypeScript

3. edge-infer-rs edge-infer-rs Public

   CPU-optimized Rust inference engine with production-style dynamic batching, dual-trigger scheduling, and backend-agnostic execution for edge ML workloads.

   Rust 4

4. mem-kv-cpp mem-kv-cpp Public

   In-memory key–value store in C++ optimized for ML inference workloads, featuring sharded concurrency, micro-batching, TTL caching, and asynchronous durability. 162k RPS, P99 <20μs.

   C++ 1

5. triton-autokernel triton-autokernel Public

   GPU kernel optimization framework using LLM-driven autotuning for Triton kernels. Benchmarks configurations and analyzes performance using roofline model on NVIDIA A100 GPUs.

   Python 1

6. BiteCheck_V2 BiteCheck_V2 Public

   An anomaly detection ML system using an XGBoost ensemble (SMOTE + ADASYN) with Optuna hyperparameter optimization for FoodHealth Company. Combines ML predictions with deterministic heuristics.

   Python