hemingkx / SWIFTLinks
[ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
☆55Updated 7 months ago
Alternatives and similar repositories for SWIFT
Users that are interested in SWIFT are comparing it to the libraries listed below
Sorting:
- ☆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
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆102Updated last year
- ☆119Updated 3 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆51Updated 11 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆32Updated 7 months ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆182Updated 3 months ago
- Multi-Candidate Speculative Decoding☆36Updated last year
- ☆28Updated 4 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆63Updated last year
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆64Updated 2 months ago
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆89Updated 10 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆50Updated 2 months ago
- ☆101Updated 2 weeks ago
- ☆52Updated last year
- ☆132Updated 3 weeks ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆202Updated 7 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆39Updated last year
- The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink…☆81Updated 2 weeks ago
- ☆27Updated 7 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆76Updated 6 months ago
- This is the official repo of "QuickLLaMA: Query-aware Inference Acceleration for Large Language Models"☆55Updated last year
- ☆86Updated 8 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆86Updated 7 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆99Updated last week
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models☆48Updated 11 months ago
- ☆60Updated 2 months ago
- ☆38Updated last year
- ☆35Updated 6 months ago
- Code for the EMNLP24 paper "A simple and effective L2 norm based method for KV Cache compression."☆16Updated 9 months ago