Lists (1)
Stars
[HPCA'26] Towards Resource-Efficient Serverless LLM Inference with SLINFER
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Foundry materializes CUDA graphs along with its execution context to disk to support fast cold start of serving engines.
A framework for generating realistic LLM serving workloads
Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average speedup of 34.93x
Step-by-step GEMM optimization, one hardware feature at a time. High performance CuTeDSL kernels for H100, B200 and RTX 50s GPUs. This repo also includes my CuTeDSL solution to MLSys26 kernel compe…
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Book in preparation: introduction to theoretical computer science
Lightweight agent multiplexer, all in one Web dashboard
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
OpenURMA: A Clean-Room Open Implementation of the Unified Bus Protocol
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
AI-powered animated comic generator — transform scripts into fully animated videos with AI-driven character design, storyboarding, and video synthesis.
Academic Research Skills for Claude Code: research → write → review → revise → finalize
Lightweight coding agent that runs in your terminal
Skills for Real Engineers. Straight from my .claude directory.
A Rust crate for cooking up terminal user interfaces (TUIs) 👨🍳🐀 https://ratatui.rs
An open-source CLI to manage your DJI Osmo device via BLE and without DJI MIMO
Engine-Agnostic Model Hot-Swapping for Cost-Effective LLM Inference
Aggregated File System (AGFS), a modern tribute to the spirit of Plan 9
Manage filesystem snapshots and allow undo of system modifications