Infini-AI-Lab / MagicDec
[ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
☆109Updated 3 months ago
Alternatives and similar repositories for MagicDec:
Users that are interested in MagicDec are comparing it to the libraries listed below
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆157Updated 8 months ago
- KV cache compression for high-throughput LLM inference☆117Updated last month
- ☆231Updated 10 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆70Updated 6 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆298Updated 8 months ago
- ☆116Updated last month
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆87Updated this week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆259Updated 4 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆89Updated last month
- 16-fold memory access reduction with nearly no loss☆81Updated this week
- Odysseus: Playground of LLM Sequence Parallelism☆66Updated 9 months ago
- ☆52Updated 11 months ago
- ☆45Updated 8 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆207Updated 7 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆51Updated 8 months ago
- LLM Serving Performance Evaluation Harness☆70Updated 3 weeks ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆148Updated 2 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆147Updated this week
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆201Updated 4 months ago
- A sparse attention kernel supporting mix sparse patterns☆164Updated last month
- PyTorch bindings for CUTLASS grouped GEMM.☆74Updated 4 months ago
- [ICLR 2025] PEARL: parallel speculative decoding with adaptive draft length☆59Updated last week
- ☆47Updated 3 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆232Updated last month
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆43Updated 8 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆279Updated 2 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆198Updated 3 months ago
- A minimal implementation of vllm.☆36Updated 7 months ago
- ☆74Updated 3 months ago