Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
☆736Apr 10, 2024Updated 2 years ago
Alternatives and similar repositories for attention_sinks
Users that are interested in attention_sinks are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆7,211Jul 11, 2024Updated last year
- YaRN: Efficient Context Window Extension of Large Language Models☆1,695Apr 17, 2024Updated 2 years ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,723Jun 25, 2024Updated last year
- Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)☆2,694Aug 14, 2024Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,329Mar 6, 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.
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆664Jun 1, 2024Updated last year
- 🤗 HuggingFace Inference Toolkit for Google Cloud Vertex AI (similar to SageMaker's Inference Toolkit, but for Vertex AI and unofficial)☆17Mar 20, 2024Updated 2 years ago
- Tools for merging pretrained large language models.☆6,973Mar 15, 2026Updated last month
- Robust recipes to align language models with human and AI preferences☆5,558Apr 8, 2026Updated last week
- Efficient few-shot learning with Sentence Transformers☆2,715Updated this week
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,175Oct 8, 2024Updated last year
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆209May 20, 2024Updated last year
- Implementation of NAACL 2024 Outstanding Paper "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"☆152Mar 13, 2025Updated last year
- Large Language Model Text Generation Inference☆10,841Mar 21, 2026Updated 3 weeks ago
- 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.
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,909Jan 21, 2024Updated 2 years ago
- LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transform…☆1,465Nov 7, 2023Updated 2 years ago
- [EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which ach…☆6,030Apr 8, 2026Updated last week
- SpanMarker for Named Entity Recognition☆469Apr 10, 2026Updated last week
- Official inference library for Mistral models☆10,773Feb 26, 2026Updated last month
- Official repository for LongChat and LongEval☆534May 24, 2024Updated last year
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,107Jun 30, 2025Updated 9 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆928Feb 26, 2026Updated last month
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆450Oct 16, 2024Updated last year
- Serverless GPU API endpoints on Runpod - Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Rectified Rotary Position Embeddings☆391May 20, 2024Updated last year
- Accessible large language models via k-bit quantization for PyTorch.☆8,121Updated this week
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,870Jun 10, 2024Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,503Jul 17, 2025Updated 9 months ago
- Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"☆1,064Mar 7, 2024Updated 2 years ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,178Updated this week
- Train transformer language models with reinforcement learning.☆18,054Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆181Jul 12, 2024Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆536Feb 10, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆309Jul 10, 2025Updated 9 months ago
- Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta☆13Nov 11, 2024Updated last year
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆5,051Apr 11, 2025Updated last year
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,983Apr 10, 2026Updated last week
- A blazing fast inference solution for text embeddings models☆4,684Updated this week
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.☆32Sep 19, 2025Updated 7 months ago
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆4,497Mar 4, 2026Updated last month