Beyond KV Caching: Shared Attention for Efficient LLMs
☆20Jul 19, 2024Updated last year
Alternatives and similar repositories for shareAtt
Users that are interested in shareAtt are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''☆31Oct 24, 2024Updated last year
- The tool facilitates debugging convergence issues and testing new algorithms and recipes for training LLMs using Nvidia libraries such as…☆19Sep 17, 2025Updated 7 months ago
- Code for the paper LeanReasoner: Boosting Complex Logical Reasoning with Lean: https://arxiv.org/pdf/2403.13312.pdf☆27May 25, 2024Updated last year
- Residual vector quantization for KV cache compression in large language model☆12Oct 22, 2024Updated last year
- ☆21Jun 1, 2025Updated 11 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆15Apr 6, 2026Updated 3 weeks ago
- Repository for Sparse Universal Transformers☆20Oct 23, 2023Updated 2 years ago
- Benchmark tests supporting the TiledCUDA library.☆18Nov 19, 2024Updated last year
- ☆11Apr 3, 2023Updated 3 years ago
- ☆22Apr 17, 2025Updated last year
- ☆92Aug 18, 2024Updated last year
- Self Reproduction Code of Paper "Reducing Transformer Key-Value Cache Size with Cross-Layer Attention (MIT CSAIL)☆17May 24, 2024Updated last year
- FPGA-based HyperLogLog Accelerator☆12Jul 13, 2020Updated 5 years ago
- [ICLR 2024] Jaiswal, A., Gan, Z., Du, X., Zhang, B., Wang, Z., & Yang, Y. Compressing llms: The truth is rarely pure and never simple.☆27Apr 21, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- 📄 Evidence Retrieval and Claim Verification for the FEVER shared task using Transformer Networks☆12Feb 21, 2020Updated 6 years ago
- Shor's algorithm simulation using CUDA☆19Nov 10, 2019Updated 6 years ago
- [WIP] Better (FP8) attention for Hopper☆33Feb 24, 2025Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆387Nov 20, 2025Updated 5 months ago
- ☆14Apr 14, 2025Updated last year
- ☆20Oct 25, 2022Updated 3 years ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆279Aug 31, 2024Updated last year
- [ICML2023] Instant Soup Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models. Ajay Jaiswal, Shiwei Liu, Ti…☆11Nov 28, 2023Updated 2 years ago
- Multilingual Semantic Search with Reranking on a prepared large vectorized dataset comprising 10 million Wikipedia documents. It supports…☆15Nov 7, 2023Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Official repository of "Distort, Distract, Decode: Instruction-Tuned Model Can Refine its Response from Noisy Instructions", ICLR 2024 Sp…☆21Mar 7, 2024Updated 2 years ago
- SmartNIC☆14Dec 13, 2018Updated 7 years ago
- TiledLower is a Dataflow Analysis and Codegen Framework written in Rust.☆13Nov 23, 2024Updated last year
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆28Apr 15, 2025Updated last year
- [ACL 2023 Findings] Emergent Modularity in Pre-trained Transformers☆26Jun 7, 2023Updated 2 years ago
- ☆311Jul 10, 2025Updated 9 months ago
- 📚 LaTeX templates and tools for creating beautiful, structured documents 📝☆14Oct 24, 2025Updated 6 months ago
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated 11 months ago
- FocusLLM: Scaling LLM’s Context by Parallel Decoding☆44Dec 8, 2024Updated last year
- 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.
- Official Implementation of UA^{2}-Agent and other baseline algorithms of "Towards Unified Alignment Between Agents, Humans, and Environme…☆19Nov 12, 2024Updated last year
- Official implementation of paper "HiAE: A High-Throughput Authenticated Encryption Algorithm for Cross-Platfor Efficiency"☆19Nov 11, 2025Updated 5 months ago
- Please visit https://github.com/HKUSTDial/NL2SQL360 to get the official code!☆10Sep 1, 2024Updated last year
- B站爬虫☆15Dec 10, 2023Updated 2 years ago
- ☆50Nov 9, 2025Updated 5 months ago
- A book about Ph.D. student and research career planning☆29Oct 21, 2025Updated 6 months ago
- Next-Generation AI-Assisted Kernel Engineering for Multi-Chip Systems☆45Apr 15, 2026Updated 2 weeks ago