SJTU-DENG-Lab / DiffulexLinks
Flexible and Pluggable Serving Engine for Diffusion LLMs
☆55Updated last week
Alternatives and similar repositories for Diffulex
Users that are interested in Diffulex are comparing it to the libraries listed below
Sorting:
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆288Updated 2 months ago
- d3LLM: Ultra-Fast Diffusion LLM 🚀☆83Updated 3 weeks ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆160Updated 3 months ago
- Block Diffusion for Ultra-Fast Speculative Decoding☆459Updated this week
- ☆129Updated 7 months ago
- ☆132Updated 8 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆197Updated 2 months ago
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆63Updated 3 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆116Updated 2 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆816Updated last week
- ☆23Updated last month
- dInfer: An Efficient Inference Framework for Diffusion Language Models☆410Updated 3 weeks ago
- Efficient triton implementation of Native Sparse Attention.☆262Updated 8 months ago
- ☆221Updated 2 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆267Updated 6 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆130Updated 2 months ago
- 🔥 A minimal training framework for scaling FLA models☆343Updated 2 months ago
- The evaluation framework for training-free sparse attention in LLMs☆114Updated last week
- ☆110Updated 4 months ago
- NexRL is an ultra-loosely-coupled LLM post-training framework.☆97Updated this week
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆400Updated this week
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆99Updated 5 months ago
- Spectral Sphere Optimizer☆90Updated 3 weeks ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆258Updated 5 months ago
- Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference☆238Updated 2 weeks ago
- Triton implementation of FlashAttention2 that adds Custom Masks.☆165Updated last year
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆188Updated 4 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆85Updated 6 months ago
- qwen-nsa☆87Updated 3 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆203Updated 2 months ago