Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind
☆111Feb 29, 2024Updated 2 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:
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆99Aug 20, 2023Updated 2 years ago
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆57Mar 26, 2024Updated 2 years ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,751Jun 25, 2024Updated 2 years ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆219Mar 5, 2026Updated 4 months ago
- ☆68Dec 3, 2024Updated last year
- 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.
- ☆22Aug 14, 2024Updated last year
- Implementation of the paper "Opcodes as predictor for malware " by Daniel Bilar☆11Oct 17, 2020Updated 5 years ago
- An approximate implementation of the OpenAI paper - An Empirical Model of Large-Batch Training for MNIST☆11Nov 19, 2022Updated 3 years ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆399Apr 22, 2025Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆165Dec 23, 2025Updated 6 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆229Feb 13, 2025Updated last year
- Synthesized singing voice demos of WeSinger 2 paper.☆26Feb 20, 2023Updated 3 years ago
- Parallel waveform generation with DiffusionGAN☆17Mar 26, 2022Updated 4 years ago
- ☆15Jun 4, 2024Updated 2 years ago
- 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.
- ☆20Feb 11, 2024Updated 2 years ago
- ☆19Jan 10, 2023Updated 3 years ago
- ☆24Mar 15, 2022Updated 4 years ago
- [ICML 2024] CLLMs: Consistency Large Language Models☆416Nov 16, 2024Updated last year
- ☆44Jun 2, 2024Updated 2 years ago
- Implementation of the paper Fast Inference from Transformers via Speculative Decoding, Leviathan et al. 2023.☆111Dec 2, 2024Updated last year
- Efficient Neural Architecture Search via Straight-Through Gradients☆13Nov 12, 2020Updated 5 years ago
- 🎉CUDA 笔记 / 高频面试题汇总 / C++笔记，个人笔记，更新随缘: sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.☆50Feb 23, 2024Updated 2 years ago
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆17Apr 24, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Toy implementations of some popular ML optimizers using Python/JAX☆44Jun 20, 2021Updated 5 years ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆50May 12, 2026Updated last month
- Implementation of FlashAttention (FA1-FA4) in PyTorch for educational and algorithmic clarity☆222Apr 12, 2026Updated 2 months ago
- The official code for Dropping Backward Propagation (DropBP)☆32Oct 29, 2024Updated last year
- [SpeechCom Journal] Learning and controlling the source-filter representation of speech with a variational autoencoder☆46Apr 18, 2023Updated 3 years ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,339Mar 6, 2025Updated last year
- ☆16Apr 11, 2024Updated 2 years ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆342Jul 2, 2024Updated 2 years ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,890Jun 27, 2026Updated last week
- 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.
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆183Jul 12, 2024Updated last year
- Multi-Candidate Speculative Decoding☆41Apr 22, 2024Updated 2 years ago
- Code for EMNLP 2021 paper: Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting☆17Nov 30, 2021Updated 4 years ago
- ☆14Dec 16, 2020Updated 5 years ago
- ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation☆25Oct 2, 2020Updated 5 years ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆71Jun 26, 2024Updated 2 years ago
- My vocoder experiments☆31Jul 26, 2025Updated 11 months ago