🔥 A minimal training framework for scaling FLA models
☆409Apr 22, 2026Updated 3 months ago
Alternatives and similar repositories for flame
Users that are interested in flame are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 🚀 Efficient implementations for emerging model architectures☆5,528Updated this week
- ☆139Feb 4, 2026Updated 6 months ago
- Code release for paper "Test-Time Training Done Right"☆501Jan 5, 2026Updated 7 months ago
- ☆139Jun 6, 2025Updated last year
- ☆35Dec 31, 2025Updated 7 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆642Mar 13, 2026Updated 4 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,017Feb 5, 2026Updated 6 months ago
- ☆285Jun 6, 2025Updated last year
- ☆71Jul 8, 2025Updated last year
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆151Feb 25, 2026Updated 5 months ago
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,193Jul 30, 2026Updated last week
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆259Jun 15, 2025Updated last year
- Accelerating MoE with IO and Tile-aware Optimizations☆737Jul 4, 2026Updated last month
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆134Jun 24, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆1,562Nov 17, 2025Updated 8 months ago
- ☆120Feb 25, 2025Updated last year
- HGRN2: Gated Linear RNNs with State Expansion☆58Aug 20, 2024Updated last year
- ☆61Jul 9, 2024Updated 2 years ago
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality☆357May 20, 2026Updated 2 months ago
- A PyTorch native platform for training generative AI models☆5,604Updated this week
- ☆253Nov 19, 2025Updated 8 months ago
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆68Apr 24, 2024Updated 2 years ago
- Minimalistic large language model 3D-parallelism training☆2,779May 26, 2026Updated 2 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Flash-Linear-Attention models beyond language☆21Aug 28, 2025Updated 11 months ago
- Here we will test various linear attention designs.☆62Apr 25, 2024Updated 2 years ago
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆20Oct 9, 2022Updated 3 years ago
- Triton implement of bi-directional (non-causal) linear attention☆78Mar 1, 2026Updated 5 months ago
- ☆45Nov 1, 2025Updated 9 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,167Updated this week
- Helpful tools and examples for working with flex-attention☆1,222Updated this week
- Tile primitives for speedy kernels☆3,621Jul 13, 2026Updated 3 weeks ago
- Ring attention implementation with flash attention☆1,045Sep 10, 2025Updated 11 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆53May 19, 2025Updated last year
- A Quirky Assortment of CuTe Kernels☆1,096Updated this week
- Official PyTorch Implementation of the Longhorn Deep State Space Model☆56Dec 4, 2024Updated last year
- Stick-breaking attention☆63Jul 1, 2025Updated last year
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆535Updated this week
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,135Updated this week
- Muon is Scalable for LLM Training☆1,528Aug 3, 2025Updated last year