FasterDecoding / MedusaLinks
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
☆2,667Updated last year
Alternatives and similar repositories for Medusa
Users that are interested in Medusa are comparing it to the libraries listed below
Sorting:
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,307Updated 8 months ago
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,872Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,362Updated 4 months ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,079Updated 5 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,276Updated 6 months ago
- Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)☆2,693Updated last year
- YaRN: Efficient Context Window Extension of Large Language Models☆1,643Updated last year
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,636Updated last year
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,753Updated this week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,221Updated last year
- Serving multiple LoRA finetuned LLM as one☆1,121Updated last year
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,629Updated last year
- Minimalistic large language model 3D-parallelism training☆2,334Updated last week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,016Updated last week
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,157Updated 2 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,195Updated 3 months ago
- ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)☆996Updated 11 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,136Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,562Updated last year
- Fast inference from large lauguage models via speculative decoding☆859Updated last year
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆2,091Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,426Updated last year
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,842Updated 2 weeks ago
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,405Updated last year
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆750Updated 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…☆1,083Updated last year
- Scalable toolkit for efficient model alignment☆847Updated last month
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,992Updated 7 months ago
- A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI☆773Updated last year
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,918Updated 3 months ago