Pinned Loading

1. Tencent/WeDLM Tencent/WeDLM Public

   WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups over vLLM-optimized baselines.

   Python 650 46

2. THU-BPM/MarkLLM THU-BPM/MarkLLM Public

   [EMNLP 2024 Demo] MarkLLM: An Open-Source Toolkit for LLM Watermarking

   Python 1k 86

3. THU-BPM/Robust_Watermark THU-BPM/Robust_Watermark Public

   [ICLR 2024] Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models".

   Python 38 8

4. THU-BPM/unforgeable_watermark THU-BPM/unforgeable_watermark Public

   [ICLR 2024] Source code of paper "An Unforgeable Publicly Verifiable Watermark for Large Language Models"

   Python 34 2

5. manaflow-ai/cmux manaflow-ai/cmux Public

   Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

   Swift 25.7k 2.2k

6. Tencent/Sequential-Hidden-Decoding Tencent/Sequential-Hidden-Decoding Public

   Official implementation of Hidden Decoding at Scale, scaling latent computation per token through multiple hidden streams while keeping the Transformer backbone fixed.

   Python 38 5