Skip to content
View hhy3's full-sized avatar

Organizations

@milvus-io

Block or report hhy3

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Starred repositories

Showing results

Agent Memory Benchmark

Python 10 2 Updated Mar 25, 2026

Scalable toolkit for efficient model reinforcement

Python 1,467 302 Updated Mar 26, 2026

Recommend new arxiv papers of your interest daily according to your Zotero libarary.

Python 4,989 4,409 Updated Mar 25, 2026

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

C++ 2,172 185 Updated Mar 26, 2026

Empowering everyone to build reliable and efficient software.

Rust 111,508 14,673 Updated Mar 26, 2026

Fast and memory-efficient exact kmeans

Python 493 25 Updated Mar 17, 2026

LLVM (Low Level Virtual Machine) Guide. Learn all about the compiler infrastructure, which is designed for compile-time, link-time, run-time, and "idle-time" optimization of programs. Originally im…

C++ 195 10 Updated Jan 4, 2024

Train the smallest LM you can that fits in 16MB. Best model wins!

Python 4,213 2,486 Updated Mar 25, 2026

A benchmark of real-world DL kernel problems

Python 122 9 Updated Mar 23, 2026

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

54 5 Updated Mar 14, 2026

FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference (ICLR'26)

Python 5 1 Updated Mar 5, 2026

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

Python 4,088 328 Updated Mar 25, 2026

Exocompilation for productive programming of hardware accelerators

Python 718 50 Updated Mar 25, 2026

Claude Code skill: Generate file-by-file code tutorial websites for any repository with parallel agent teams

24 1 Updated Mar 13, 2026

CLI-Anything: Making ALL Software Agent-Native

Python 23,186 2,054 Updated Mar 26, 2026

Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

Python 835 70 Updated Mar 19, 2026

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Python 1,764 166 Updated Mar 26, 2026

The repo for SOSP23 paper: FIFO queues are all you need for cache evictions

C 138 16 Updated Jun 13, 2024

Common recipes to run vLLM

Jupyter Notebook 521 177 Updated Mar 16, 2026

你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候,对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

TypeScript 12,073 634 Updated Mar 25, 2026

OpenClaw-RL: Train any agent simply by talking

Python 4,215 418 Updated Mar 25, 2026

SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models

Python 123 37 Updated Mar 26, 2026

DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference

Python 616 38 Updated Nov 24, 2025

an educational compiler intermediate representation

Rust 746 326 Updated Feb 6, 2026

AI agents running research on single-GPU nanochat training automatically

Python 56,253 7,836 Updated Mar 26, 2026

advanced compilers

HTML 906 220 Updated Jan 10, 2026

TiDB - the open-source, cloud-native, distributed SQL database designed for modern applications.

Go 39,926 6,155 Updated Mar 26, 2026

Elevate your AI research writing, no more tedious polishing ✨

13,990 1,087 Updated Mar 25, 2026

practice made claude perfect

HTML 22,057 1,914 Updated Mar 25, 2026
Next