wangqinsi1 / CoreInfer
This is the official Python version of CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation.
☆15Updated 5 months ago
Alternatives and similar repositories for CoreInfer:
Users that are interested in CoreInfer are comparing it to the libraries listed below
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆23Updated last month
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆35Updated 9 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆35Updated 7 months ago
- ☆47Updated 3 months ago
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆67Updated last month
- [ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference☆19Updated last week
- ☆50Updated 10 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆176Updated last month
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆68Updated 2 months ago
- ☆8Updated 6 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆265Updated 4 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆45Updated last month
- ☆17Updated 4 months ago
- Multi-Candidate Speculative Decoding☆35Updated 11 months ago
- ☆52Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆157Updated 8 months ago
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models☆42Updated 4 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆57Updated 6 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆94Updated last month
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆85Updated last year
- official code for GliDe with a CaPE☆13Updated 7 months ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆103Updated 2 weeks ago
- 16-fold memory access reduction with nearly no loss☆86Updated this week
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆67Updated 2 weeks ago
- My own implementation of "Fast Inference from Transformers via Speculative Decoding"☆11Updated last year
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆80Updated last month
- ☆39Updated 4 months ago
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆86Updated 10 months ago
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆21Updated 6 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆47Updated last year