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:
- ☆20Updated 2 years ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆47Updated 2 months ago
- ☆93Updated 3 years ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆90Updated 2 years ago
- GPU operators for sparse tensor operations☆35Updated last year
- ☆113Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆46Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- ☆26Updated 2 years ago
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆86Updated 7 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆130Updated 10 months ago
- ☆88Updated 3 years ago
- ☆59Updated 10 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆82Updated last year
- ☆47Updated last year
- A resilient distributed training framework☆95Updated last year
- ☆143Updated 7 months ago
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆12Updated 3 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆59Updated 11 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆40Updated last year
- ☆72Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆185Updated last year
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆60Updated last year
- ☆56Updated last year
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆21Updated last year
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆50Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆80Updated 11 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆242Updated last week
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 6 months ago
- Code associated with the paper **Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees**.☆27Updated 2 years ago