hao-ai-lab / LookaheadDecodingLinks
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
☆1,249Updated 2 months ago
Alternatives and similar repositories for LookaheadDecoding
Users that are interested in LookaheadDecoding are comparing it to the libraries listed below
Sorting:
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,266Updated last week
- Serving multiple LoRA finetuned LLM as one☆1,060Updated last year
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,530Updated 11 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆611Updated last year
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆725Updated 8 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,035Updated this week
- Large Context Attention☆711Updated 4 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,119Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,417Updated 10 months ago
- YaRN: Efficient Context Window Extension of Large Language Models☆1,489Updated last year
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,823Updated last year
- Scalable toolkit for efficient model alignment☆803Updated last week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆827Updated 8 months ago
- distributed trainer for LLMs☆575Updated last year
- Ring attention implementation with flash attention☆771Updated last week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,009Updated 2 months ago
- Minimalistic large language model 3D-parallelism training☆1,888Updated last week
- Microsoft Automatic Mixed Precision Library☆602Updated 8 months ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆808Updated last week
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆688Updated 9 months ago
- ☆534Updated 9 months ago
- Fast inference from large lauguage models via speculative decoding☆738Updated 9 months ago
- A throughput-oriented high-performance serving framework for LLMs☆814Updated 3 weeks ago
- A simple and effective LLM pruning approach.☆752Updated 9 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,174Updated 2 weeks ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,029Updated 3 weeks ago
- [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baich…☆1,014Updated 7 months ago
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆799Updated 9 months ago
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,534Updated last year
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆697Updated last year