nil0x9 / flash-muonLinks
Flash-Muon: An Efficient Implementation of Muon Optimizer
☆189Updated 3 months ago
Alternatives and similar repositories for flash-muon
Users that are interested in flash-muon are comparing it to the libraries listed below
Sorting:
- ☆126Updated 4 months ago
- 🔥 A minimal training framework for scaling FLA models☆255Updated 3 weeks ago
- The evaluation framework for training-free sparse attention in LLMs☆98Updated 3 months ago
- ☆249Updated 3 months ago
- ☆89Updated 7 months ago
- Fast and memory-efficient exact attention☆70Updated 7 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆115Updated 3 months ago
- Efficient triton implementation of Native Sparse Attention.☆226Updated 4 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆241Updated last month
- ☆142Updated 7 months ago
- Triton implementation of FlashAttention2 that adds Custom Masks.☆135Updated last year
- Odysseus: Playground of LLM Sequence Parallelism☆77Updated last year
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆308Updated 2 weeks ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆241Updated last month
- Low-bit optimizers for PyTorch☆131Updated last year
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆92Updated 9 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆89Updated 2 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆143Updated 4 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆43Updated 3 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆249Updated this week
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆234Updated 2 months ago
- Normalized Transformer (nGPT)☆191Updated 10 months ago
- ☆41Updated 5 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated 10 months ago
- ☆149Updated 2 years ago
- Work in progress.☆74Updated 3 months ago
- Load compute kernels from the Hub☆290Updated last week
- Some preliminary explorations of Mamba's context scaling.☆217Updated last year
- Muon fsdp 2☆44Updated last month
- ring-attention experiments☆152Updated 11 months ago