ChandlerGuan / TranskimmerLinks
Code for ACL2022 publication Transkimmer: Transformer Learns to Layer-wise Skim
☆21Updated 2 years ago
Alternatives and similar repositories for Transkimmer
Users that are interested in Transkimmer are comparing it to the libraries listed below
Sorting:
- Multi-Candidate Speculative Decoding☆35Updated last year
- ☆50Updated last year
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆51Updated last year
- [ACL 2024] Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"☆44Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated 2 months ago
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆92Updated last year
- ☆14Updated last year
- ☆74Updated 4 years ago
- [KDD'22] Learned Token Pruning for Transformers☆98Updated 2 years ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆60Updated 8 months ago
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆22Updated 9 months ago
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆26Updated 2 months ago
- official code for GliDe with a CaPE☆19Updated 10 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆90Updated 2 months ago
- ☆14Updated last year
- ☆54Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆194Updated 4 months ago
- ☆42Updated 7 months ago
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆39Updated 3 months ago
- ☆42Updated 2 years ago
- ☆16Updated 2 months ago
- xKV: Cross-Layer SVD for KV-Cache Compression☆27Updated last week
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆88Updated 2 years ago
- ☆30Updated last month
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆57Updated last year
- ☆84Updated 3 years ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆79Updated 5 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆40Updated 6 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆163Updated 11 months ago
- ☆52Updated 6 months ago