thunlp / Ouroboros
Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
☆102Updated last month
Alternatives and similar repositories for Ouroboros:
Users that are interested in Ouroboros are comparing it to the libraries listed below
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆51Updated 9 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆77Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆115Updated 4 months ago
- ☆237Updated 11 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆159Updated 9 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆199Updated 4 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆183Updated 2 months ago
- Multi-Candidate Speculative Decoding☆35Updated last year
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆42Updated 5 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆85Updated this week
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆23Updated 2 months ago
- ☆122Updated 2 months ago
- ☆48Updated 4 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆72Updated 7 months ago
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆93Updated last year
- Async pipelined version of Verl☆60Updated 2 weeks ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆148Updated 2 weeks ago
- Odysseus: Playground of LLM Sequence Parallelism☆68Updated 10 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆270Updated 5 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆209Updated 8 months ago
- ☆43Updated last year
- Repository of LV-Eval Benchmark☆63Updated 7 months ago
- ☆39Updated 4 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆45Updated 6 months ago
- Cascade Speculative Drafting☆29Updated last year
- 16-fold memory access reduction with nearly no loss☆90Updated 3 weeks ago
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆25Updated last week
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆85Updated last year
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆99Updated 2 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆72Updated 2 months ago