Stars
LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
The agent that grows with you
Train the smallest LM you can that fits in 16MB. Best model wins!
The batteries-included agent harness.
Hundreds of models & providers. One command to find what runs on your hardware.
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.
Open Source Continuous Inference Benchmark Research Platform — Kimi K3 2.8T, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3 | 开源持续推理基准研究平台…
Learn Low Level Design (LLD) and prepare for interviews using free resources.
PyTorch library for cost-effective, fast and easy serving of MoE models.
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Code for Bolmo: Byteifying the Next Generation of Language Models
MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation Model
My learning notes for ML SYS.
A minimal tensor processing unit (TPU), inspired by Google's TPU V2 and V1
[ICLR 2026] Astra : General Interactive World Model with Autoregressive Denoising"
An open source implementation of code execution with MCP (Programatic Tool Calling)
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
Tangle is a web app that allows the users to build and run Machine Learning pipelines without having to set up development environment.
A general memory system for agents, powered by deep-research
🚀 An awesome list of curated Nano Banana pro prompts and examples. Your go-to resource for mastering prompt engineering and exploring the creative potential of the Nano banana pro(Nano banana 2) AI…
GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.
Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI.
Cloud Native Agentic AI | Discord: https://bit.ly/kagentdiscord
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations