hao-ai-lab / DynasorLinks
Simple extension on vLLM to help you speed up reasoning model without training.
☆177Updated 2 months ago
Alternatives and similar repositories for Dynasor
Users that are interested in Dynasor are comparing it to the libraries listed below
Sorting:
- KV cache compression for high-throughput LLM inference☆134Updated 6 months ago
- ☆85Updated 7 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆109Updated 5 months ago
- ☆273Updated last month
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆124Updated 8 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆169Updated last year
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆231Updated 8 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆487Updated 6 months ago
- ☆117Updated 2 months ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆118Updated last year
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆188Updated 2 months ago
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆66Updated last year
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆72Updated 5 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆429Updated 3 months ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆145Updated last month
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆147Updated 2 weeks ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆91Updated 2 months ago
- [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.☆43Updated 3 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☆31Updated 6 months ago
- Repo for "Z1: Efficient Test-time Scaling with Code"☆63Updated 4 months ago
- ☆139Updated 6 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆48Updated 10 months ago
- Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?☆115Updated 10 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆207Updated 8 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆220Updated last month
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆240Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆133Updated 3 months ago
- ☆127Updated 3 months ago
- ☆201Updated 8 months ago