Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing (Technical Report)
☆39Jul 10, 2026Updated 3 months ago
Alternatives and similar repositories for linear-attention-architectures
Users that are interested in linear-attention-architectures are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- https://arxiv.org/abs/2610.13990☆32Oct 15, 2026Updated last week
- [ACL 2026] Official repo for "Native Hybrid Attention for Efficient Sequence Modeling"☆33Sep 17, 2026Updated last month
- SGLang 0.5.21 for Qwen3.8-Flash-Next on one RTX PRO 6000: 264.5 tok/s decode, W4A16 routed experts (KLD 0.0111 vs BF16), 262K context, ex…☆17Oct 12, 2026Updated last week
- 更纯粹、更高压缩率的Tokenizer in Rust☆14Sep 7, 2026Updated last month
- Uni-Agent is a framework for training long-horizon agents.☆24Sep 21, 2026Updated last month
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆57Sep 27, 2026Updated 3 weeks ago
- Code and data to explore neural scaling laws of xLSTM and Transformer models.☆24Apr 8, 2026Updated 6 months ago
- Official Codebase: LT2: Linear-Time Looped Transformers.☆65Jul 27, 2026Updated 2 months ago
- How fast can you write a Google Protocol Buffer (signed) VarInt?☆13May 9, 2021Updated 5 years ago
- A rust based risc-v operating system!☆11Feb 12, 2026Updated 8 months ago
- Checkpointable dataset utilities for foundation model training☆32Jan 29, 2024Updated 2 years ago
- Flash-Flash KDA: H100-optimized Flash Kimi Delta Attention kernels☆24Jul 24, 2026Updated 2 months ago
- [Tech Report, NeurIPS 2026] Expanded Hyper-Connections☆75Updated this week
- Code for the paper: https://arxiv.org/pdf/2309.06979.pdf☆21Jul 29, 2024Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- DeepStack: Facilitating Co-Design Exploration of 3D DRAM-Stacked Accelerators for Distributed LLM Inference. Includes the MICRO 2026 AE a…☆65Oct 5, 2026Updated 2 weeks ago
- Official PyTorch Implementation of Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention☆344Oct 11, 2026Updated last week
- This is a repository dedicated to high quality figures from ICLR 2025 papers.☆11Dec 15, 2025Updated 10 months ago
- An R interface to LSEG Workspace, Refinitiv Eikon, and Refinitiv DataStream☆12Updated this week
- Communication patterns for AI, built on top of NCCL device and host APIs☆70Updated this week
- Efficient Mask-Aware Distributed Attention for Long-Context Training☆52Updated this week
- Training-free inference acceleration framework for interactive video world models, with tested support for HY-WorldPlay and Matrix-Game-3…☆23Jun 18, 2026Updated 4 months ago
- [ICLR 2026] Any-step Generation via N-th Order Recursive Consistent Velocity Field Estimation☆42Feb 4, 2026Updated 8 months ago
- ☆10Sep 23, 2024Updated 2 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- T5 model optimized with FlexAttention☆14Sep 30, 2024Updated 2 years ago
- ☆20Dec 24, 2024Updated last year
- NaiveRT: a self-contained TP8 inference runtime for the Naive N series on eight Blackwell GPUs with UMMA support. One persistent CUDA gra…☆30Sep 27, 2026Updated 3 weeks ago
- [ICLR 2026] Multi-Head Low-Rank Attention☆33Apr 16, 2026Updated 6 months ago
- Delta Attention Residuals - supplementary code and pretrained models☆43Sep 26, 2026Updated 3 weeks ago
- ☆28May 20, 2026Updated 5 months ago
- 本人自用的SDK☆14Sep 11, 2026Updated last month
- Dist-MoE implements Speed-of-Light distributed Mixture-of-Experts forward and backward kernels. They are highly optimized and fused comm-…☆17Updated this week
- ☆29Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Scripts and documentation on scaling large language model training on the LUMI supercomputer☆10Jun 30, 2023Updated 3 years ago
- GTNH Factory Flow planner and dataset automation☆62Updated this week
- 10606 Fall 2023☆14Oct 13, 2023Updated 3 years ago
- Lightweight self-hosted web search & extract service for Hermes Agent, a drop-in Firecrawl alternative☆65Sep 25, 2026Updated 3 weeks ago
- A linker for partial GPU kernels.☆31Oct 12, 2026Updated last week
- Implementation of the proposed CCBP (Continuous Continual BackProp) in Pytorch☆12Sep 3, 2026Updated last month
- [ICML 2025] RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression☆55Aug 7, 2025Updated last year