Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".
☆48Jul 12, 2024Updated 2 years ago
Alternatives and similar repositories for ExCP
Users that are interested in ExCP are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- LLM checkpointing for DeepSpeed/Megatron☆27Nov 30, 2025Updated 11 months ago
- Code for paper "Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation" (ICLR'24)☆13Nov 17, 2023Updated 2 years ago
- Phoenix is a direct hub between storage and xPU — plug in any accelerator (GPU/NPU) or AI app and stream data straight to the chip.☆29Oct 26, 2026Updated last week
- [SIGIR 2024] This is the official PyTorch implementation for the paper: "EulerFormer: Sequential User Behavior Modeling with Complex Vect…☆18Oct 5, 2024Updated 2 years ago
- ☆15Jan 21, 2023Updated 3 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [EMNLP24]LPZero: Language Model Zero-Cost Proxy Search from Zero☆11Oct 21, 2024Updated 2 years ago
- This the implementation of LeCo☆33Jan 20, 2025Updated last year
- ☆12Sep 1, 2023Updated 3 years ago
- [EMNLP 2023 Industry Track] A simple prompting approach that enables the LLMs to run inference in batches.☆76Mar 8, 2024Updated 2 years ago
- Low-bit optimizers for PyTorch☆140Oct 9, 2023Updated 3 years ago
- ☆15Sep 24, 2023Updated 3 years ago
- Reduce kernel based on CUTLASS CuTe and TMA.☆12Sep 25, 2025Updated last year
- Pytorch code for paper: Full-Stack Filters to Build Minimum Viable CNNs☆16Sep 10, 2019Updated 7 years ago
- A tracing tool to analyze the I/O behavior of a program.☆12Sep 25, 2019Updated 7 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- arXiv 2024 | ZIP: entropy-law data selection for efficient LLM alignment.☆28Jun 10, 2026Updated 4 months ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆71Mar 27, 2025Updated last year
- This is the official PyTorch implementation for the paper: "Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledg…☆14Mar 5, 2023Updated 3 years ago
- [AAAI2023] NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension☆17Dec 20, 2022Updated 3 years ago
- [ICML'24] The official implementation of “Rethinking Optimization and Architecture for Tiny Language Models”☆127Jan 14, 2025Updated last year
- [SIGIR 2024] This is the official PyTorch implementation for the paper: "EulerFormer: Sequential User Behavior Modeling with Complex Vect…☆11Oct 1, 2024Updated 2 years ago
- [WSDM 2023] This is the official PyTorch implementation for the paper: "Directed Acyclic Graph Factorization Machines for CTR Prediction …☆18Mar 5, 2023Updated 3 years ago
- Crawl & visualize ICLR papers and reviews.☆18Nov 5, 2022Updated 3 years ago
- [KDD24-ADS] R-Eval: A Unified Toolkit for Evaluating Domain Knowledge of Retrieval Augmented Large Language Models☆11Apr 9, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [NeurIPS 2024] Search for Efficient LLMs☆16Jan 16, 2025Updated last year
- ☆19Jan 3, 2025Updated last year
- Sequence-level 1F1B schedule for LLMs.☆37Aug 26, 2025Updated last year
- ☆51Mar 2, 2024Updated 2 years ago
- Official code for the paper "HEXA-MoE: Efficient and Heterogeneous-Aware MoE Acceleration with Zero Computation Redundancy"☆16Mar 6, 2025Updated last year
- Pruning the VLLMs☆105Dec 9, 2024Updated last year
- High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU [SIGMOD'26]☆32Oct 20, 2026Updated last week
- Crail: a fast multi-tiered distributed storage system☆11Aug 21, 2022Updated 4 years ago
- [arXiv 2024] I4VGen: Image as Free Stepping Stone for Text-to-Video Generation☆24Oct 6, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- The reproduce for "AM-LFS: AutoML for Loss Function Search"☆14May 20, 2020Updated 6 years ago
- [ICLR 2025] Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better☆16Feb 15, 2025Updated last year
- The official implementation code of the CIKM 2024 paper "Sequence-level Semantic Representation Fusion for Recommender Systems".☆16Mar 28, 2025Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆17Updated this week
- Artifacts for our NSDI'23 paper TGS☆98Jun 10, 2024Updated 2 years ago
- VaniDL is an tool for analyzing I/O patterns and behavior with Deep Learning Applications.☆10Jul 8, 2022Updated 4 years ago
- This is the repository for our AgentSearch Benchmark. The official website is https://bingo-w.github.io/AgentSearchBench/☆16Jul 23, 2026Updated 3 months ago