NoakLiu / MT2STLinks
Accelerating Multitask Training Trough Adaptive Transition [Efficient ML Model]
☆12Updated 3 months ago
Alternatives and similar repositories for MT2ST
Users that are interested in MT2ST are comparing it to the libraries listed below
Sorting:
- Adaptive Topology Reconstruction for Robust Graph Representation Learning [Efficient ML Model]☆10Updated 6 months ago
- Efficient Foundation Model Design: A Perspective From Model and System Co-Design [Efficient ML System & Model]☆25Updated 6 months ago
- GraphSnapShot: Caching Local Structure for Fast Graph Learning [Efficient ML System]☆35Updated 2 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆92Updated 2 months ago
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆82Updated 6 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆47Updated last month
- Code repo for efficient quantized MoE inference with mixture of low-rank compensators☆22Updated 4 months ago
- ☆18Updated 6 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆63Updated last month
- ☆25Updated 5 months ago
- Official PyTorch implementation of the paper "Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Princ…☆29Updated last month
- ☆56Updated 9 months ago
- The official implementation of "Helen: Optimizing CTR Prediction Models with Frequency-wise Hessian Eigenvalue Regularization"☆16Updated last year
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆80Updated 2 months ago
- ☆45Updated 9 months ago
- Multi-Candidate Speculative Decoding☆36Updated last year
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆93Updated 2 months ago
- 16-fold memory access reduction with nearly no loss☆104Updated 5 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆43Updated last year
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆74Updated 5 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆110Updated 4 months ago
- ThinK: Thinner Key Cache by Query-Driven Pruning☆23Updated 6 months ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆64Updated 5 months ago
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models☆46Updated 10 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆32Updated 6 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆49Updated last month
- ☆21Updated 3 years ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆90Updated 2 years ago
- A family of efficient edge language models in 100M~1B sizes.☆16Updated 6 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆53Updated 6 months ago