Code for the paper *Attention Drift: What Speculative Decoding Models Learn*.
☆27May 12, 2026Updated 2 months ago
Alternatives and similar repositories for Attention-Drift
Users that are interested in Attention-Drift are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆21May 19, 2025Updated last year
- [ICCV 2025] A Benchmark for Multi-Step Reasoning in Long Narrative Videos☆28Jun 4, 2026Updated last month
- TurboServe: Serving Streaming Video Generation Efficiently and Economically☆29Updated this week
- ☆24Oct 15, 2024Updated last year
- 常用的ocr数据集☆16Nov 15, 2021Updated 4 years ago
- 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.
- Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆118Jun 24, 2026Updated 2 weeks ago
- Fork of Flame repo for training of some new stuff in development☆20Jul 2, 2026Updated last week
- ☆27May 3, 2024Updated 2 years ago
- A PyTorch native library for training speculative decoding models☆200Updated this week
- Code for data-aware compression of DeepSeek models☆75Dec 11, 2025Updated 7 months ago
- PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant with Reliable References☆21Jun 13, 2024Updated 2 years ago
- [ACL '26 Findings] V-MAGE: A Game Evaluation Framework for Assessing Visual-Centric Capabilities in MLLMs☆27Apr 28, 2026Updated 2 months ago
- Official Repo for paper "VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference"☆16Mar 28, 2026Updated 3 months ago
- Accurate and fast KV cache compression with a gating mechanism☆26Apr 5, 2026Updated 3 months 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.
- (IJCV 2023) Offical implementation of "SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels"☆13Mar 20, 2025Updated last year
- ☆20Mar 29, 2023Updated 3 years ago
- Open-source Human Feedback Library☆11Oct 25, 2023Updated 2 years ago
- ☆24Jun 18, 2025Updated last year
- a common lisp library for data analysis and manipulation☆12May 28, 2023Updated 3 years ago
- Thread-Safe Pools / Distributed Pools for Common Lisp.☆16Jan 20, 2026Updated 5 months ago
- [CVPR 2023] Better “CMOS” Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution☆10Mar 19, 2024Updated 2 years ago
- ☆34Oct 4, 2024Updated last year
- ☆48Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Instant Neural Graphics Primitives from scratch, zero dependencies. Learning by doing.☆10Aug 18, 2023Updated 2 years ago
- ☆16Jun 15, 2026Updated 3 weeks ago
- SIMD implementation of argmin and argmax☆12Jul 2, 2024Updated 2 years ago
- ☆40Oct 31, 2025Updated 8 months ago
- 面向多平台编译优化的深度学习中间表示☆10Oct 28, 2024Updated last year
- Share your GPU without MIG or MPS☆50Jan 27, 2026Updated 5 months ago
- An implementation of the Augmented Random Search algorithm☆14Jan 29, 2022Updated 4 years ago
- Evaluation Code repository for the paper "ModuLoRA: Finetuning 3-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers". (2023…☆13Dec 5, 2023Updated 2 years ago
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆56Mar 14, 2025Updated last year
- 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.
- ☆12Nov 11, 2019Updated 6 years ago
- ☆10Dec 8, 2021Updated 4 years ago
- Clustered Compositional Embeddings☆13Oct 25, 2023Updated 2 years ago
- ☆17Apr 10, 2024Updated 2 years ago
- [ICLR 2026] - Official implementation of "Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency"☆33Feb 23, 2026Updated 4 months ago
- Read and write Numpy .npy and .npz files.☆18Sep 19, 2023Updated 2 years ago
- A CLI tool for managing your locally downloaded Huggingface models and datasets☆35Aug 19, 2025Updated 10 months ago