Omc12
Follow
-
Differential-KV Public
Differential-KV (DKV) is a sparse KV-cache inference runtime designed for high-efficiency, memory-bounded long-context Large Language Model (LLM) inference across Apple Silicon (MLX) and CUDA GPUs.
-
-
-
TensorRT-LLM Public
Forked from NVIDIA/TensorRT-LLMTensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
Python Other UpdatedSep 7, 2026 -
CRBench Public
CRBench is a method-agnostic benchmark for long-context LLMs that measures contextual capability retained relative to a dense reference alongside memory and system resource efficiency.
Python MIT License UpdatedAug 28, 2026 -
-
sktime-mcp Public
Forked from sktime/sktime-mcpAn MCP (Model Context Protocol) layer that exposes sktime’s native registry and semantics to an LLM
Python BSD 3-Clause "New" or "Revised" License UpdatedApr 29, 2026 -
-
Caelum Public
Caelum is a sky photo enhancement project built in PyTorch. It trains a lightweight Attention + Residual U-Net to transform dull/hazy/under-saturated sky photos into cleaner, more vibrant results w…
Python UpdatedApr 16, 2026 -
Mavis Public
Forked from DhruvR-16/MavisMavis is an intelligent fitness assistant that provides gym-grade coaching right from any standard webcam device.
Python UpdatedMar 19, 2026 -
RAG retrieval ablation study (semantic/hybrid/MMR) for stock-news QA; evaluates coverage, grounding, relevance. Zenodo: https://zenodo.org/records/19086005
machine-learning research maximum-marginal-relevance rag semantic-retrieval retrieval-augmented-generationPython UpdatedMar 18, 2026 -
Company-Intelligence-Engine Public
AI-powered analysis of SEC filings that produces structured company intelligence (risks, strengths, competitive advantage, outlook) using a hybrid retrieval + reranking pipeline and LLM reasoning c…
-
-
VibeGuard Public
VibeGuard (CLI: vibecheck) is a developer tool designed to close the feedback loop between AI coding agents and the running application. It combines a file watcher, an MCP (Model Context Protocol) …
TypeScript UpdatedFeb 16, 2026 -
openclaw Public
Forked from openclaw/openclawYour own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
TypeScript MIT License UpdatedFeb 16, 2026 -
Signalist Public
AI-powered stock insights for Indian (NSE) stocks. Features machine learning predictions with 99 technical + fundamental features, real-time data from Yahoo Finance, and a modern React frontend.
-
-
MarketSentinel Public
MarketSentinel features a Retrieval-Augmented Generation (RAG) architecture built with Python, powered by Streamlit for web interface, sentence-transformers for semantic search, and Google Gemini f…
Python UpdatedFeb 4, 2026 -
RAG-stock-news Public
This project implements a Retrieval Augmented Generation (RAG) system for stock news analysis using a hybrid retrieval strategy.
Python UpdatedFeb 2, 2026 -
StockSimple Public
Small Business Stock Tracker & Reorder Alert System
JavaScript UpdatedJan 14, 2026 -
UIDAI-Data-Hackathon Public
Forked from DhruvR-16/UIDAI-Data-HackathonJupyter Notebook UpdatedJan 14, 2026 -
UIDAI-Forcasts Public
An adaptive statistical ensemble designed for short, volatile operational data optimized for stability and actionability validated by backtesting.
Jupyter Notebook UpdatedJan 13, 2026 -
Layout-Generator Public
Layout-Generator features a rule-based generative architecture built with Python, powered by Matplotlib for visualization, NumPy for computational processing, and scikit-learn's NearestNeighbors fo…
Python UpdatedJan 9, 2026 -
AQI_Pred_Model Public
This model is designed to predict Air Quality Index (AQI) values by analyzsing historical and real-time environmental data, providing actionable insights to help monitor and mitigate air pollution.
Python UpdatedNov 5, 2025 -
-
-
-
-
shortUrl Public
ShortUrl is a simple and efficient URL shortening service developed using JavaScript and EJS.
JavaScript UpdatedJun 8, 2025 -