hao-ai-lab / LookaheadDecodingLinks
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
☆1,282Updated 6 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☆1,093Updated last year
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,635Updated last year
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆631Updated last year
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆747Updated last year
- YaRN: Efficient Context Window Extension of Large Language Models☆1,613Updated last year
- Large Context Attention☆742Updated 8 months ago
- Microsoft Automatic Mixed Precision Library☆622Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,133Updated this week
- Scalable toolkit for efficient model alignment☆842Updated 2 months ago
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,854Updated last year
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,605Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆902Updated last year
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆837Updated last year
- Fast inference from large lauguage models via speculative decoding☆829Updated last year
- Ring attention implementation with flash attention☆885Updated 3 weeks ago
- distributed trainer for LLMs☆580Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,512Updated last year
- ☆570Updated last year
- A simple and effective LLM pruning approach.☆803Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,192Updated last year
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,063Updated 3 months ago
- ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)☆992Updated 10 months ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆854Updated 4 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…☆1,066Updated 11 months ago
- Automatically split your PyTorch models on multiple GPUs for training & inference☆655Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆703Updated last year
- Minimalistic large language model 3D-parallelism training☆2,239Updated last month
- ☆547Updated 9 months ago
- For releasing code related to compression methods for transformers, accompanying our publications☆446Updated 8 months ago
- A throughput-oriented high-performance serving framework for LLMs☆894Updated 2 weeks ago