ruikangliu / IntactKV
Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"
☆43Updated 10 months ago
Alternatives and similar repositories for IntactKV:
Users that are interested in IntactKV are comparing it to the libraries listed below
- [AAAI 2024] Fluctuation-based Adaptive Structured Pruning for Large Language Models☆47Updated last year
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆72Updated 2 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆49Updated last year
- ☆50Updated 11 months ago
- [ICLR 2024] Jaiswal, A., Gan, Z., Du, X., Zhang, B., Wang, Z., & Yang, Y. Compressing llms: The truth is rarely pure and never simple.☆23Updated last year
- More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression☆11Updated 3 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆51Updated 9 months ago
- [ICML 2024 Oral] This project is the official implementation of our Accurate LoRA-Finetuning Quantization of LLMs via Information Retenti…☆64Updated last year
- ☆39Updated 4 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆46Updated 5 months ago
- ☆50Updated last year
- AFPQ code implementation☆20Updated last year
- Multi-Candidate Speculative Decoding☆35Updated 11 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆36Updated 8 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆181Updated 2 months ago
- ☆75Updated last week
- ☆19Updated 3 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆62Updated 6 months ago
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"☆64Updated 9 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆127Updated 2 months ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆54Updated 3 weeks ago
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆109Updated 11 months ago
- ☆20Updated 5 months ago
- SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆19Updated 6 months ago
- ☆53Updated last year
- Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''☆25Updated 5 months ago
- LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification☆45Updated last month
- [NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.☆156Updated 6 months ago
- Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLM…☆47Updated last year
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆45Updated 2 months ago