linfeng93 / BiTALinks
An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.
☆26Updated 9 months ago
Alternatives and similar repositories for BiTA
Users that are interested in BiTA are comparing it to the libraries listed below
Sorting:
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆113Updated 10 months ago
- ☆158Updated 11 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆176Updated last year
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆65Updated last year
- ☆51Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆214Updated 11 months ago
- ☆300Updated 6 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆137Updated last year
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆65Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆93Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year
- Multi-Candidate Speculative Decoding☆39Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆221Updated last year
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆105Updated last year
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆214Updated 4 months ago
- KV cache compression for high-throughput LLM inference☆150Updated 11 months ago
- 16-fold memory access reduction with nearly no loss☆109Updated 10 months ago
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆96Updated last year
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆39Updated 11 months ago
- [ACL 2024] Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"☆48Updated last year
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆56Updated last year
- Unofficial implementations of block/layer-wise pruning methods for LLMs.☆77Updated last year
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆88Updated 11 months ago
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆21Updated last year
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆132Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆52Updated 5 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆44Updated last year
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆49Updated 6 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆335Updated last year
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆401Updated last year