ScalingIntelligence / hydragenLinks
Hydragen: High-Throughput LLM Inference with Shared Prefixes
☆41Updated last year
Alternatives and similar repositories for hydragen
Users that are interested in hydragen are comparing it to the libraries listed below
Sorting:
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆116Updated 6 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆77Updated 9 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆217Updated 6 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆163Updated 11 months ago
- ☆106Updated last week
- ☆129Updated 3 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆94Updated 2 weeks ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆57Updated 11 months ago
- ☆76Updated last month
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆110Updated 3 weeks ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆106Updated 2 months ago
- A minimal implementation of vllm.☆41Updated 10 months ago
- 16-fold memory access reduction with nearly no loss☆96Updated 2 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 8 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated 11 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated last month
- extensible collectives library in triton☆87Updated 2 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated last month
- ☆86Updated 2 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆212Updated last year
- KV cache compression for high-throughput LLM inference☆130Updated 4 months ago
- ☆105Updated 9 months ago
- ☆253Updated last year
- ☆71Updated 3 weeks ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆135Updated 10 months ago
- ☆81Updated 7 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆210Updated 9 months ago
- LLM Serving Performance Evaluation Harness☆78Updated 3 months ago
- ☆49Updated 3 weeks ago