Infini-AI-Lab / MagicPIGLinks
[ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation
☆248Updated last year
Alternatives and similar repositories for MagicPIG
Users that are interested in MagicPIG are comparing it to the libraries listed below
Sorting:
- ☆302Updated 6 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆176Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆141Updated last year
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆188Updated 4 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆370Updated 6 months ago
- ☆158Updated 11 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆160Updated 3 months ago
- KV cache compression for high-throughput LLM inference☆151Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆356Updated 2 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆154Updated 11 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆523Updated 11 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆218Updated 8 months ago
- 16-fold memory access reduction with nearly no loss☆110Updated 10 months ago
- KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches. EMNLP Findings 2024☆88Updated 11 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆402Updated last year
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆260Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆335Updated last year
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆155Updated 3 weeks ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆289Updated 3 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆113Updated 10 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆215Updated 4 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆148Updated last year
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆88Updated 10 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆569Updated 2 weeks ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆147Updated last month
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆278Updated last week
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆131Updated 2 months ago
- ☆132Updated 8 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆116Updated 2 months ago
- ☆353Updated last year