Infini-AI-Lab / MagicDecLinks
[ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
☆116Updated 6 months ago
Alternatives and similar repositories for MagicDec
Users that are interested in MagicDec are comparing it to the libraries listed below
Sorting:
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆113Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆163Updated 11 months ago
- 16-fold memory access reduction with nearly no loss☆99Updated 3 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆79Updated 9 months ago
- ☆130Updated 4 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆106Updated 3 months ago
- ☆256Updated last year
- ☆77Updated 2 months ago
- ☆54Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆46Updated 8 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆210Updated 10 months ago
- KV cache compression for high-throughput LLM inference☆131Updated 4 months ago
- ☆114Updated 3 weeks ago
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆310Updated 11 months ago
- ☆87Updated 3 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆112Updated this week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆297Updated 7 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆57Updated last year
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆123Updated 4 months ago
- ☆47Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆149Updated 2 months ago
- LLM Serving Performance Evaluation Harness☆78Updated 4 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated last month
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆90Updated 2 months ago
- A minimal implementation of vllm.☆44Updated 11 months ago
- ☆67Updated 8 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆100Updated 3 weeks ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆51Updated last year
- ☆159Updated this week