FasterDecoding / Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
☆2,512Updated 10 months ago
Alternatives and similar repositories for Medusa:
Users that are interested in Medusa are comparing it to the libraries listed below
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,242Updated last month
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,818Updated last year
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,004Updated last month
- Serving multiple LoRA finetuned LLM as one☆1,057Updated 11 months ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,197Updated last week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,956Updated last week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,121Updated this week
- YaRN: Efficient Context Window Extension of Large Language Models☆1,470Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,093Updated last year
- Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)☆2,652Updated 8 months ago
- [NeurIPS'24 Spotlight, ICLR'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which r…☆985Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,152Updated this week
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,724Updated 4 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,394Updated 9 months ago
- Fast inference from large lauguage models via speculative decoding☆718Updated 8 months ago
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,514Updated last year
- [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baich…☆1,002Updated 6 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆601Updated last year
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆692Updated last year
- Minimalistic large language model 3D-parallelism training☆1,808Updated this week
- A simple and effective LLM pruning approach.☆738Updated 8 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆719Updated 7 months ago
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,378Updated last year
- FlashInfer: Kernel Library for LLM Serving☆2,731Updated this week
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆651Updated 10 months ago
- An Open-source Toolkit for LLM Development☆2,774Updated 3 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆809Updated 7 months ago
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,718Updated 8 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,251Updated this week
- LOMO: LOw-Memory Optimization☆985Updated 9 months ago