hao-ai-lab / DynasorLinks
[NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
☆197Updated 4 months ago
Alternatives and similar repositories for Dynasor
Users that are interested in Dynasor are comparing it to the libraries listed below
Sorting:
- ☆280Updated 2 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆172Updated last year
- ☆86Updated 8 months ago
- KV cache compression for high-throughput LLM inference☆141Updated 8 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 6 months ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆238Updated 9 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆128Updated 10 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆491Updated 7 months ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆116Updated last year
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆32Updated 7 months ago
- [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.☆47Updated 5 months ago
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆381Updated last year
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆210Updated 3 weeks ago
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆67Updated last year
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆249Updated this week
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆443Updated 4 months ago
- ☆119Updated 3 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆76Updated 6 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆146Updated 2 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆155Updated 5 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆155Updated last week
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆42Updated last week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆192Updated 3 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆220Updated 2 weeks ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆338Updated 5 months ago
- Implementation of NAACL 2024 Outstanding Paper "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"☆149Updated 6 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆202Updated 7 months ago
- [ICML 2024] CLLMs: Consistency Large Language Models☆404Updated 10 months ago
- Async pipelined version of Verl☆117Updated 5 months ago