hemingkx / SWIFTLinks
[ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
☆55Updated 8 months ago
Alternatives and similar repositories for SWIFT
Users that are interested in SWIFT are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆52Updated 11 months ago
- ☆46Updated 11 months ago
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆96Updated 4 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆33Updated 8 months ago
- Multi-Candidate Speculative Decoding☆36Updated last year
- ☆133Updated last month
- The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink…☆95Updated last month
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆106Updated last year
- ☆28Updated 3 weeks ago
- ☆119Updated 4 months ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆186Updated 3 months ago
- ☆18Updated 10 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆56Updated 3 weeks ago
- LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models☆76Updated last year
- ☆104Updated last month
- ☆29Updated 5 months ago
- ☆44Updated 3 weeks ago
- ☆52Updated last year
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆86Updated 8 months ago
- [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression☆112Updated 6 months ago
- This is the official repo of "QuickLLaMA: Query-aware Inference Acceleration for Large Language Models"☆55Updated last year
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆40Updated last year
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆64Updated last year
- ☆85Updated 9 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆205Updated 8 months ago
- ☆40Updated 7 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆65Updated 3 months ago
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆88Updated 10 months ago
- ☆20Updated 10 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆106Updated last month