Infini-AI-Lab / TriForce
[COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding
☆247Updated 7 months ago
Alternatives and similar repositories for TriForce:
Users that are interested in TriForce are comparing it to the libraries listed below
- ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆157Updated 5 months ago
- MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction☆87Updated 5 months ago
- ☆235Updated 11 months ago
- [ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2☆197Updated 3 weeks ago
- Support mixed-precsion inference with vllm☆83Updated 3 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆269Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆159Updated 9 months ago
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆221Updated 6 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆288Updated 2 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆181Updated 2 months ago
- A sparse attention kernel supporting mix sparse patterns☆186Updated 2 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆51Updated 9 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆113Updated 4 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆101Updated 3 weeks ago
- ☆122Updated 2 months ago
- 16-fold memory access reduction with nearly no loss☆89Updated 3 weeks ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆71Updated 2 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆82Updated last week
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆438Updated 8 months ago
- ☆48Updated 4 months ago
- Unified KV Cache Compression Methods for Auto-Regressive Models☆1,001Updated 3 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆303Updated 9 months ago
- APOLLO: SGD-like Memory, AdamW-level Performance☆202Updated last month
- ☆39Updated 4 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆85Updated last year
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆70Updated last month
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆99Updated last month
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆36Updated 8 months ago
- ☆60Updated 6 months ago
- ☆53Updated last year