Infini-AI-Lab / MagicPIG
MagicPIG: LSH Sampling for Efficient LLM Generation
β45Updated 2 weeks ago
Related projects β
Alternatives and complementary repositories for MagicPIG
- Awesome-LLM-KV-Cache: A curated list of πAwesome LLM KV Cache Papers with Codes.β96Updated this week
- Multi-Candidate Speculative Decodingβ28Updated 6 months ago
- β36Updated last month
- β34Updated 2 months ago
- π° Must-read papers on KV Cache Compression (constantly updating π€).β123Updated this week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inferenceβ196Updated last week
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**β135Updated 5 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLMβ146Updated 4 months ago
- 16-fold memory access reduction with nearly no lossβ57Updated this week
- β42Updated 7 months ago
- Puzzles for learning Triton, play it with minimal environment configuration!β61Updated this week
- Code for Palu: Compressing KV-Cache with Low-Rank Projectionβ56Updated this week
- β31Updated 2 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.β101Updated 2 months ago
- β70Updated 2 years ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".β74Updated last year
- QAQ: Quality Adaptive Quantization for LLM KV Cacheβ42Updated 7 months ago
- β51Updated last month
- Implementation of Kangaroo: Lossless Self-Speculative Decoding via Double Early Exitingβ41Updated 4 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inferenceβ35Updated this week
- β43Updated last month
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)β76Updated 3 weeks ago
- β63Updated 3 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)β183Updated 2 weeks ago
- Materials for learning SGLangβ86Updated this week
- β183Updated 6 months ago
- A sparse attention kernel supporting mix sparse patternsβ53Updated 3 weeks ago
- TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attentionβ21Updated last month
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inferenceβ25Updated 4 months ago
- β42Updated 4 months ago