PyTorch DeepSeek Sparse Attention (DSA) training & inference
☆23Oct 14, 2025Updated 10 months ago
Alternatives and similar repositories for deepseek-sparse-attention-pytorch
Users that are interested in deepseek-sparse-attention-pytorch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DeepSeek Native Sparse Attention pytorch implementation☆119Dec 17, 2025Updated 8 months ago
- Efficient triton implementation of Native Sparse Attention.☆282May 23, 2025Updated last year
- 微信小程序之记事本☆11Jun 6, 2018Updated 8 years ago
- [WIP] Better (FP8) attention for Hopper☆33Aug 21, 2026Updated last week
- ☆19Jan 2, 2026Updated 7 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆12Dec 27, 2022Updated 3 years ago
- Hardware CD/CI and Development Containers 🚢☆11Jul 20, 2022Updated 4 years ago
- KimiaPath24: Dataset for retrieval and classification in digital pathology☆13Jun 4, 2017Updated 9 years ago
- my solution for UC Berkeley AI projects pacman☆11Jul 25, 2020Updated 6 years ago
- ☆16Dec 11, 2025Updated 8 months ago
- Scientific Computing in Python, a practical and ultimate tutorials☆14Mar 7, 2023Updated 3 years ago
- RSI expert advisor for MT5 - a template-based EA to create and test your own RSI trading system.☆14Mar 4, 2024Updated 2 years ago
- ☆17Mar 10, 2026Updated 5 months ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆13May 30, 2024Updated 2 years ago
- Accurate encoding of histologic images into StyleGAN space for discovery and explainability☆13Oct 8, 2025Updated 10 months ago
- An implementation is provided here for the NeurIPS2024 paper "MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected…☆16Mar 24, 2026Updated 5 months ago
- Self Reproduction Code of Paper "Reducing Transformer Key-Value Cache Size with Cross-Layer Attention (MIT CSAIL)☆17May 24, 2024Updated 2 years ago
- Knowledge extraction from semi-structured web.☆13Mar 25, 2024Updated 2 years ago
- Easy-to-Hard Learning for Information Extraction (ACL 2023 Findings)☆14Jul 11, 2023Updated 3 years ago
- ☆16Dec 16, 2021Updated 4 years ago
- ☆16Apr 9, 2021Updated 5 years ago
- dynamic planning, hybrid models, hierarchical active inference, tool use☆15Jun 13, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Jul 17, 2026Updated last month
- The code of SRIBD-Med Team for NeurIPS2022 Cell Segmentation Challenge☆15Jul 23, 2023Updated 3 years ago
- Position sensitive PreciseRoIPooling without roi coordinates gradient backward☆16Aug 2, 2018Updated 8 years ago
- pytorch implementation of DeepSeek Engram☆19Mar 24, 2026Updated 5 months ago
- Training/Evaluation code for HoVer-NeXt☆18Updated this week
- ☆15Jul 16, 2024Updated 2 years ago
- ☆23Apr 2, 2023Updated 3 years ago
- Package Xilinx FPGA tools into docker containers, useful for CI situations.☆17Oct 20, 2014Updated 11 years ago
- Hyperledger Indy/Sovrin/DID Comprehensive Architecture Reference Model (INDY ARM) - Draft document for discussion purposes☆14Jan 25, 2021Updated 5 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Official Repo for paper "VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference"☆15Mar 28, 2026Updated 5 months ago
- SC'25 UltraAttn: Efficiently Parallelizing Attention through Hierarchical Context-Tiling☆16Aug 14, 2025Updated last year
- Unofficial Scalable-Softmax Is Superior for Attention☆21May 30, 2025Updated last year
- a simple web of data visualization☆11Feb 18, 2023Updated 3 years ago
- BESA is a differentiable weight pruning technique for large language models.☆17Mar 4, 2024Updated 2 years ago
- Caffe fork with unpool layers, deconvolution layers, locally connected layers, and a custom layer called TweakFeaturesLayer.☆13Apr 16, 2016Updated 10 years ago
- Project used python☆11Jun 30, 2024Updated 2 years ago