FasterDecoding / Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
☆2,312Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for Medusa
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,149Updated last month
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,755Updated 10 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,526Updated last month
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆1,765Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆2,613Updated this week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆1,941Updated 7 months ago
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆826Updated this week
- YaRN: Efficient Context Window Extension of Large Language Models☆1,353Updated 7 months ago
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,391Updated 8 months ago
- Serving multiple LoRA finetuned LLM as one☆984Updated 6 months ago
- ☆1,271Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,904Updated this week
- Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)☆2,638Updated 3 months ago
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,008Updated 10 months ago
- FlashInfer: Kernel Library for LLM Serving☆1,452Updated this week
- Fast inference from large lauguage models via speculative decoding☆569Updated 2 months ago
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆2,205Updated this week
- Minimalistic large language model 3D-parallelism training☆1,260Updated this week
- A simple and effective LLM pruning approach.☆669Updated 3 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,257Updated 4 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,045Updated 10 months ago
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,336Updated 7 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆647Updated last month
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆675Updated 7 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,893Updated last month
- [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baich…☆874Updated last month
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,497Updated last month
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆558Updated 8 months ago
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆721Updated 3 months ago