DS3Lab / AC-SGDLinks
Code associated with the paper **Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees**.
☆28Updated 2 years ago
Alternatives and similar repositories for AC-SGD
Users that are interested in AC-SGD are comparing it to the libraries listed below
Sorting:
- ☆52Updated 6 months ago
- ☆57Updated last year
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆38Updated 10 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆88Updated 2 years ago
- [ICDCS 2023] Evaluation and Optimization of Gradient Compression for Distributed Deep Learning☆10Updated 2 years ago
- ☆19Updated 2 years ago
- ☆20Updated 2 years ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆39Updated last year
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆35Updated 2 years ago
- ☆37Updated 9 months ago
- Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs☆19Updated 6 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆71Updated 8 months ago
- The implementation for MLSys 2023 paper: "Cuttlefish: Low-rank Model Training without All The Tuning"☆45Updated 2 years ago
- ☆27Updated last year
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated 11 months ago
- ☆50Updated last year
- ☆26Updated 7 months ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆61Updated 2 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆47Updated 7 months ago
- [ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference☆24Updated last week
- PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models. ICML 2021☆56Updated 3 years ago
- ☆42Updated 2 years ago
- [ICLR 2025] Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better☆15Updated 4 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated 2 months ago
- 16-fold memory access reduction with nearly no loss☆99Updated 3 months ago
- GPU operators for sparse tensor operations☆33Updated last year
- [ICLR 2024] Jaiswal, A., Gan, Z., Du, X., Zhang, B., Wang, Z., & Yang, Y. Compressing llms: The truth is rarely pure and never simple.☆24Updated 2 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆54Updated 3 months ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Updated 7 months ago
- ☆84Updated 3 years ago