hao-ai-lab / LookaheadDecodingLinks
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
☆1,315Updated 10 months ago
Alternatives and similar repositories for LookaheadDecoding
Users that are interested in LookaheadDecoding are comparing it to the libraries listed below
Sorting:
- Serving multiple LoRA finetuned LLM as one☆1,135Updated last year
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆637Updated last year
- Large Context Attention☆762Updated 3 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,174Updated 3 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆750Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆987Updated last year
- Scalable toolkit for efficient model alignment☆847Updated 3 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,694Updated last year
- YaRN: Efficient Context Window Extension of Large Language Models☆1,664Updated last year
- Microsoft Automatic Mixed Precision Library☆635Updated last month
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆865Updated last year
- Ring attention implementation with flash attention☆967Updated 4 months ago
- ☆586Updated last year
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,896Updated 2 years ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,590Updated last year
- A simple and effective LLM pruning approach.☆845Updated last year
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆886Updated 2 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…☆1,103Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,247Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆940Updated 2 months ago
- distributed trainer for LLMs☆588Updated last year
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,653Updated last year
- Fast inference from large lauguage models via speculative decoding☆884Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆712Updated last year
- ☆551Updated last year
- Minimalistic large language model 3D-parallelism training☆2,422Updated last month
- Automatically split your PyTorch models on multiple GPUs for training & inference☆657Updated 2 years ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆907Updated last month
- For releasing code related to compression methods for transformers, accompanying our publications☆454Updated last year
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,090Updated 6 months ago