Simple implementation of Speculative Sampling in NumPy for GPT-2.
☆98Aug 20, 2023Updated 3 years ago
Alternatives and similar repositories for speculative-sampling
Users that are interested in speculative-sampling are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Explorations into some recent techniques surrounding speculative decoding☆307Dec 22, 2024Updated last year
- Fast inference from large lauguage models via speculative decoding☆926Aug 22, 2024Updated 2 years ago
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆99Feb 6, 2024Updated 2 years ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆230Feb 13, 2025Updated last year
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆112Feb 29, 2024Updated 2 years 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.
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆410Apr 22, 2025Updated last year
- Code for the "Long Context Needs Some R&R" paper.☆12Mar 11, 2024Updated 2 years ago
- Beyond LM: How can language model go forward in the future?☆15Apr 30, 2023Updated 3 years ago
- BERT models for many languages created from Wikipedia texts☆33May 25, 2020Updated 6 years ago
- An implementation of SGEMV with performance comparable to cuBLAS.☆12May 21, 2021Updated 5 years ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,771Jun 25, 2024Updated 2 years ago
- This repository is the official implementation of "Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE" [ACL 2026 Mai…☆38Oct 5, 2025Updated 10 months ago
- An experimental implementation of the retrieval-enhanced language model☆74Dec 29, 2022Updated 3 years ago
- ☆23Jul 10, 2023Updated 3 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Simple speculative decoding technique, integrated in vLLM and transformers☆616Aug 23, 2024Updated 2 years ago
- AskUp Search ChatGPT Plugin☆20May 27, 2023Updated 3 years ago
- Cascade Speculative Drafting☆33Apr 2, 2024Updated 2 years ago
- Calculating Expected Time for training LLM.☆39Apr 17, 2023Updated 3 years ago
- ☆13Jun 18, 2024Updated 2 years ago
- LLMs playing chess are sensitive to how the position came to be☆25Feb 14, 2024Updated 2 years ago
- Minimal RLHF implementation built on top of minGPT.☆32Jul 4, 2024Updated 2 years ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆723Aug 13, 2024Updated 2 years ago
- Talking Face Generation system☆17Oct 16, 2023Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- A Python library that tees the standard output & standard error from the current process to files on disk, while preserving terminal sema…☆16Aug 17, 2023Updated 3 years ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,342Mar 6, 2025Updated last year
- ☆25Mar 19, 2022Updated 4 years ago
- Auxiliary tasks for task-oriented dialogue systems. Published in ICNLSP'22 and indexed in the ACL Anthology.☆17Feb 27, 2023Updated 3 years ago
- ☆39Mar 25, 2024Updated 2 years ago
- ☆109Jun 20, 2023Updated 3 years ago
- annotated-transformer-kr☆15May 16, 2019Updated 7 years ago
- ☆44Apr 22, 2026Updated 4 months ago
- Implementation of the paper Fast Inference from Transformers via Speculative Decoding, Leviathan et al. 2023.☆116Dec 2, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [HCLT 2022] Korean sentence text similarity dataset using naver shopping review☆25Oct 20, 2022Updated 3 years ago
- A minimalist Docker project to help people getting started with Node, WizardCoder, CTransformers, Python, Express and TypeScript. Ready t…☆14Jun 23, 2023Updated 3 years ago
- Efficient LLM Inference over Long Sequences☆392Jun 25, 2025Updated last year
- CareCall for Seniors: Role Specified Open-Domain Dialogue dataset generated by leveraging LLMs (NAACL 2022).☆62May 3, 2022Updated 4 years ago
- ☆15May 14, 2019Updated 7 years ago
- This PyTorch package implements MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation (NAACL 2022).☆114May 2, 2022Updated 4 years ago
- ☆20Nov 3, 2024Updated last year