FasterDecoding / Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
☆2,426Updated 7 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☆1,194Updated 4 months ago
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,790Updated last year
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆1,946Updated last month
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,743Updated last week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆2,911Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,965Updated last week
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆968Updated this week
- Serving multiple LoRA finetuned LLM as one☆1,028Updated 9 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,031Updated 10 months ago
- YaRN: Efficient Context Window Extension of Large Language Models☆1,421Updated 10 months ago
- FlashInfer: Kernel Library for LLM Serving☆2,078Updated this week
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,446Updated 11 months ago
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,654Updated last month
- Minimalistic large language model 3D-parallelism training☆1,483Updated this week
- Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)☆2,646Updated 6 months ago
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,498Updated 3 months ago
- Fast inference from large lauguage models via speculative decoding☆657Updated 5 months ago
- LOMO: LOw-Memory Optimization☆980Updated 7 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,339Updated 7 months ago
- [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baich…☆953Updated 4 months ago
- [NeurIPS'24 Spotlight, ICLR'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which r…☆917Updated last week
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆767Updated 4 months ago
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,361Updated 10 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,083Updated last year
- A simple and effective LLM pruning approach.☆712Updated 6 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆584Updated 11 months ago
- Reference implementation for DPO (Direct Preference Optimization)☆2,377Updated 6 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆701Updated 4 months ago
- distributed trainer for LLMs☆557Updated 9 months ago
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆767Updated 6 months ago