FFY0/DefensiveKV
Official Implementation for [ICLR26] DefensiveKV: Taming the Fragility of KV Cache Eviction in LLM Inference
PhD Candidate @ USTC
Repositories
FFY0/AdaKV
The Official Implementation of Ada-KV [NeurIPS 2025]
FFY0/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
FFY0/Qwen3-Omni
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
FFY0/hermes-agent
The agent that grows with you
FFY0/LegoSketch_ICML
The Official Implementation of LegoSketch [ICML 2025]
FFY0/MetaSketch_TPAMI
SourceCode for MetaSketch
FFY0/cua
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
FFY0/yuanfeng.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
FFY0/meta-sketch
FFY0/claw-code
The fastest repo in history to surpass 50K stars ⭐, reaching the milestone in just 2 hours after publication. Better Harness Tools that make real things done. Now writing in Rust using oh-my-codex.
FFY0/AdaKV-in-NVIDIA-kvpress
A custom implementation of [AdaKV](https://arxiv.org/abs/2407.11550) under the open-source project NVIDIA/kvpress. Original AdaKV code can be found in [repo](https://github.com/FFY0/AdaKV). Additionally, [NVIDIA/kvpress](https://github.com/NVIDIA/kvpress) also offers a simpler method to simulate the performance of AdaKV.
FFY0/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
FFY0/adakvcompress
KV cache compression for high-throughput LLM inference