sail-sg / LongSpecLinks
LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
☆64Updated 2 months ago
Alternatives and similar repositories for LongSpec
Users that are interested in LongSpec are comparing it to the libraries listed below
Sorting:
- ☆119Updated 4 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆49Updated 11 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆51Updated 11 months ago
- The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink…☆83Updated 2 weeks ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆32Updated 7 months ago
- ☆60Updated 2 months ago
- ☆38Updated last year
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆249Updated last week
- ☆43Updated 4 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆80Updated 2 months ago
- ☆101Updated 2 weeks ago
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆22Updated 11 months ago
- ☆96Updated 3 weeks ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆39Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 6 months ago
- ☆45Updated 10 months ago
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆94Updated 3 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆54Updated 10 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆99Updated last week
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆50Updated 2 months ago
- ☆25Updated 2 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆46Updated last year
- ☆10Updated last year
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆55Updated 7 months ago
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆76Updated 6 months ago
- ☆52Updated last year
- ☆28Updated 4 months ago
- Code for the preprint "Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?"☆46Updated 2 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆143Updated 4 months ago