Highlights
- Pro
Lists (2)
Stars
Official repo of paper "SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models". A post-training framework that creates a cost-effective, self-iterative optimization loop.
Another ChatGLM2 implementation for GPTQ quantization
Recommend new arxiv papers of your interest daily according to your Zotero libarary.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Because `model.fit()` isn't an explanation
[ICRA 2026] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
Official inference framework for 1-bit LLMs
Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.
Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
BlackHole is a modern macOS audio loopback driver that allows applications to pass audio to other applications with zero additional latency.
Video translation and dubbing tool powered by LLMs. The video translator offers 100 language translations and one-click full-process deployment. The video translation output is optimized for platfo…
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
💫 Toolkit to help you get started with Spec-Driven Development
An open-source, AI-integrated, cross-platform terminal for seamless workflows
A free, open source, and extensible speech-to-text application that works completely offline.
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
[ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
A simple black/white hexo theme for novel reading.
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.