hao-ai-lab / DynasorLinks
Simple extension on vLLM to help you speed up reasoning model without training.
☆169Updated 2 months ago
Alternatives and similar repositories for Dynasor
Users that are interested in Dynasor are comparing it to the libraries listed below
Sorting:
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆167Updated last year
- ☆82Updated 6 months ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆228Updated 7 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆480Updated 5 months ago
- KV cache compression for high-throughput LLM inference☆134Updated 5 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆123Updated 8 months ago
- ☆268Updated 3 weeks ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆141Updated 3 weeks ago
- [NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models☆174Updated 7 months ago
- [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.☆40Updated 3 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆183Updated last month
- ☆79Updated last week
- The official repo for "LLoCo: Learning Long Contexts Offline"☆118Updated last year
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆66Updated last year
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆417Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆29Updated 5 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆109Updated 4 months ago
- ☆113Updated last month
- Repo for "Z1: Efficient Test-time Scaling with Code"☆63Updated 3 months ago
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆237Updated 11 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆124Updated 2 months ago
- ☆199Updated 7 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆140Updated 2 weeks ago
- Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?☆112Updated 9 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆205Updated 8 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆72Updated 4 months ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆323Updated 3 months ago
- ☆136Updated 5 months ago
- Tina: Tiny Reasoning Models via LoRA☆272Updated 2 months ago