### Overall Goal 1. Improve open-source project infrastructure 2. Fix existing bugs and stabilize service/API 3. Add quantifiable regression tests 4. Support new feature integration, such as KV cache, streaming inference, and distributed inference ### 🧠 New Model Integrations - [ ] [Cosmos3](https://github.com/NVIDIA/cosmos) @Uxito-Ada - [ ] [Mage](https://github.com/microsoft/Mage/tree/main) - [ ] [TaoMate](https://github.com/TaoLiveAIGC/TaoMate) - [ ] [Wan-Animate-2](https://github.com/Wan-Video/Wan-Animate-2) - [ ] [RelayVSR](https://github.com/[kopperx/RelayVSR](https://github.com/kopperx/RelayVSR)) ### New Feature Support - [ ] Chunk Batching @Kaimary - [ ] Multi-instance KV cache with fp8 or fp4 quant @Uxito-Ada - [ ] Disaggregated Inference - [ ] Multi-instance server support - [ ] improve sheduler and server with rust refactor ### ⚡ Performance & Kernels - [ ] NVF4 for world model @Uxito-Ada - [ ] NPU support https://github.com/Tele-AI/TeleFuser/pull/41 ---
Activity