Infini-AI-Lab / MagicDec
[ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
☆107Updated 2 months ago
Alternatives and similar repositories for MagicDec:
Users that are interested in MagicDec are comparing it to the libraries listed below
- ☆220Updated 9 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆157Updated 7 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆84Updated 4 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆64Updated 5 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆245Updated 2 months ago
- KV cache compression for high-throughput LLM inference☆115Updated 2 weeks ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆295Updated 7 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆205Updated 6 months ago
- ☆111Updated this week
- 16-fold memory access reduction with nearly no loss☆76Updated 3 months ago
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆75Updated 2 weeks ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆48Updated 7 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆132Updated this week
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆272Updated last month
- ☆43Updated 7 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆64Updated 8 months ago
- LLM Serving Performance Evaluation Harness☆68Updated this week
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆192Updated 2 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆196Updated 2 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆42Updated 4 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆148Updated 3 weeks ago
- ☆67Updated 2 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆229Updated this week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆332Updated 6 months ago
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆53Updated 8 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆193Updated 3 months ago
- ☆52Updated 10 months ago
- A minimal implementation of vllm.☆33Updated 6 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆199Updated last year