DS3Lab / Decentralized_FM_alphaLinks
☆19Updated 2 years ago
Alternatives and similar repositories for Decentralized_FM_alpha
Users that are interested in Decentralized_FM_alpha are comparing it to the libraries listed below
Sorting:
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆93Updated 2 years ago
- ☆20Updated 2 years ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆175Updated last year
- GPU operators for sparse tensor operations☆35Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆47Updated last year
- ☆94Updated 3 years ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆49Updated 4 months ago
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆14Updated 5 months ago
- ☆115Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆135Updated last year
- ☆27Updated 2 years ago
- A resilient distributed training framework☆96Updated last year
- ☆88Updated 3 years ago
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆43Updated last year
- Vortex: A Flexible and Efficient Sparse Attention Framework☆43Updated 3 weeks ago
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆87Updated 10 months ago
- ☆156Updated 10 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆219Updated last year
- ☆63Updated last year
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆21Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆146Updated last year
- ☆48Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆89Updated last year
- Dynamic Context Selection for Efficient Long-Context LLMs☆47Updated 7 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆66Updated last year
- Hydragen: High-Throughput LLM Inference with Shared Prefixes☆45Updated last year
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆55Updated last week
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆71Updated last year