#
Starred repositories
NOFX: Defining the Next-Generation AI Trading Operating System. A multi-exchange Al trading platform(Binance/Hyperliquid/Aster) with multi-Ai competition(deepseek/qwen/claude)self-evolution, and re…
OpenRecall is a fully open-source, privacy-first alternative to proprietary solutions like Microsoft's Windows Recall. With OpenRecall, you can easily access your digital history, enhancing your me…
Generate a timeline of your day, automatically
Awesome curated collection of images and prompts generated by gemini-2.5-flash-image (aka Nano Banana) state-of-the-art image generation and editing model. Explore AI generated visuals created with…
Selective Prompt Anchoring
A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.
Sample cloud-first application with 10 microservices showcasing Kubernetes, Istio, and gRPC.
cluster data collected from production clusters in Alibaba for cluster management research
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.
Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models
Official PyTorch implementation of DLP: Dynamic Layerwise Pruning in Large Language Models(ICML'25)
A hybrid and high-performance layer-7 load balancing system.
LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale
A language for constraint-guided and efficient LLM programming.
[AAAI 2025] Official Implementation of "Auto-Regressive Moving Diffusion Models for Time Series Forecasting"
One‑click codebase “blast” for Large‑Language‑Model workflows.
P4runpro: Enabling Runtime Programmability for RMT Switches
Artifact evaluation repo for EuroSys'24.
Build resilient language agents as graphs.
CHAI is a library for dynamic pruning of attention heads for efficient LLM inference.
Lets make video diffusion practical!
This is the repository for Direct Telemetry Access, a high-speed network telemetry collection system.
Disaggregated serving system for Large Language Models (LLMs).
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.