(Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints" (https://arxiv.org/pdf/2305.13245.pdf)
☆194May 9, 2024Updated 2 years ago
Alternatives and similar repositories for grouped-query-attention-pytorch
Users that are interested in grouped-query-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:
- several types of attention modules written in PyTorch for learning purposes☆55Jan 2, 2026Updated 5 months ago
- The open source implementation of the multi grouped query attention by the paper "GQA: Training Generalized Multi-Query Transformer Model…☆16Dec 11, 2023Updated 2 years ago
- ☆20Oct 25, 2022Updated 3 years ago
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆18Mar 15, 2024Updated 2 years ago
- Explore how to get a VQ-VAE models efficiently!☆70Jul 24, 2025Updated 11 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆20May 30, 2024Updated 2 years ago
- ☆10Dec 28, 2023Updated 2 years ago
- Time Series Representation Models☆13Jul 17, 2025Updated 11 months ago
- Nearest Neighbor Normalization (EMNLP 2024)☆21Nov 1, 2024Updated last year
- Leveraging BERT to Improve Spoken Language Identification☆18Nov 22, 2022Updated 3 years ago
- A spoken version of the textual story cloze benchmark☆22Aug 6, 2023Updated 2 years ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆92Jun 18, 2024Updated 2 years ago
- Official Implementation of ACL2023: Don't Parse, Choose Spans! Continuous and Discontinuous Constituency Parsing via Autoregressive Span …☆14Aug 25, 2023Updated 2 years ago
- RoFormer V1 & V2 pytorch☆526May 18, 2022Updated 4 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.
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆75May 26, 2024Updated 2 years ago
- An Experiment on Dynamic NTK Scaling RoPE☆65Nov 26, 2023Updated 2 years ago
- ☆14Nov 15, 2022Updated 3 years ago
- ☆48Mar 31, 2024Updated 2 years ago
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆139Apr 30, 2024Updated 2 years ago
- PyTorch implementation for PaLM: A Hybrid Parser and Language Model.☆10Jan 7, 2020Updated 6 years ago
- 📥 🎯 (1,4/4) an MLIR-based toolchain with Vitis HLS LLVM input/output targeting FPGAs.☆15Nov 15, 2022Updated 3 years ago
- Ongoing Research Project for continaual pre-training LLM(dense mode)☆46Mar 3, 2025Updated last year
- ☆14Oct 3, 2024Updated last year
- 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.
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆19Oct 9, 2022Updated 3 years ago
- Computes loss between two sets of entities using the optimal assignment based on the Hungarian algorithm.☆16Mar 31, 2026Updated 2 months ago
- semantic tokenizer for speech and music☆21Jul 6, 2025Updated 11 months ago
- [ICLR 2026] Data Pipeline, Models, and Benchmark for Omni-Captioner.☆138Apr 7, 2026Updated 2 months ago
- ☆20Oct 4, 2024Updated last year
- faster inference☆28Jan 20, 2025Updated last year
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆50Jun 16, 2023Updated 3 years ago
- [NeurIPS 2024] Official Implementation of "SDformer: Similarity-driven Discrete Transformer For Time Series Generation"☆16May 23, 2025Updated last year
- [ECCV 2024] "REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models"☆13Aug 6, 2024Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,692Mar 8, 2024Updated 2 years ago
- ☆30Apr 8, 2025Updated last year
- [KDD 2026] Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe☆40Aug 10, 2025Updated 10 months ago
- ☆26Apr 18, 2025Updated last year
- ☆36Sep 6, 2025Updated 9 months ago
- Source code for Leveraging 2D Information for Long-term Time Series Forecasting with Vanilla Transformers☆19May 29, 2024Updated 2 years ago
- ☆39Apr 5, 2024Updated 2 years ago