Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind
☆110Feb 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
Sorting:
- Fast inference from large lauguage models via speculative decoding☆899Aug 22, 2024Updated last year
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,145Mar 9, 2026Updated last week
- 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 last year
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,719Jun 25, 2024Updated last year
- ☆22Aug 14, 2024Updated last year
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆372Apr 22, 2025Updated 11 months ago
- An approximate implementation of the OpenAI paper - An Empirical Model of Large-Batch Training for MNIST☆11Nov 19, 2022Updated 3 years ago
- Synthesized singing voice demos of WeSinger 2 paper.☆26Feb 20, 2023Updated 3 years ago
- Parallel waveform generation with DiffusionGAN☆17Mar 26, 2022Updated 3 years ago
- Implementation of the paper "Variable Bitrate Residual Vector Quantization for Audio Coding"☆11Apr 10, 2025Updated 11 months ago
- Easily spot, fix and detect badly written code in your project without breaking a sweat. Your GPT4 and LLM powered programming AI realtim…☆21Mar 2, 2025Updated last year
- ☆20Feb 11, 2024Updated 2 years ago
- Qwen3-0.6B megakernel: 527 tok/s decode on RTX 3090 (3.8x faster than PyTorch)☆82Feb 10, 2026Updated last month
- Implementation of the paper Fast Inference from Transformers via Speculative Decoding, Leviathan et al. 2023.☆101Dec 2, 2024Updated last year
- ☆19Jan 10, 2023Updated 3 years ago
- [ICML 2024] CLLMs: Consistency Large Language Models☆413Nov 16, 2024Updated last year
- ☆44Jun 2, 2024Updated last year
- ☆16Dec 14, 2022Updated 3 years ago
- Efficient Neural Architecture Search via Straight-Through Gradients☆13Nov 12, 2020Updated 5 years ago
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆18Apr 24, 2024Updated last year
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆44Feb 13, 2025Updated last year
- Implementation of FlashAttention in PyTorch☆182Jan 12, 2025Updated last year
- Source code for the paper "Flexible 3GPP MIMO Channel Modeling and Calibration with Spatial Consistency"☆12Aug 6, 2023Updated 2 years ago
- G2pw's inference speed is accelerated by about 8-10 times. Change loop generated predictive data to only once and model loop prediction b…☆14Dec 30, 2023Updated 2 years ago
- code repo for EMNLP'21 Finding Counter-Interference Adapter for Multilingual Machine Translation☆18Oct 19, 2022Updated 3 years ago
- [SpeechCom Journal] Learning and controlling the source-filter representation of speech with a variational autoencoder☆45Apr 18, 2023Updated 2 years ago
- The official code for Dropping Backward Propagation (DropBP)☆32Oct 29, 2024Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,322Mar 6, 2025Updated last year
- DEPRECATED version of SoundFile☆14May 26, 2020Updated 5 years ago
- Source code of APNet2, a vocoder☆58Nov 23, 2023Updated 2 years ago
- NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates [WIP]☆25Jul 5, 2022Updated 3 years ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆336Jul 2, 2024Updated last year
- ☆17Apr 11, 2024Updated last year
- Multi-Candidate Speculative Decoding☆40Apr 22, 2024Updated last year
- A user-friendly and efficient knowledge distillation framework for LLMs.☆53Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆180Jul 12, 2024Updated last year
- Code for EMNLP 2021 paper: Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting☆17Nov 30, 2021Updated 4 years ago
- ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation☆25Oct 2, 2020Updated 5 years ago