Code for studying the super weight in LLM
☆124Dec 3, 2024Updated last year
Alternatives and similar repositories for LLMSuperWeight
Users that are interested in LLMSuperWeight are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code accompanying the paper "Massive Activations in Large Language Models"☆205Mar 4, 2024Updated 2 years ago
- [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization☆40Sep 24, 2024Updated 2 years ago
- ☆26Oct 31, 2024Updated 2 years ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆395Apr 13, 2025Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆55Oct 18, 2024Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Code for the paper "A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis"☆20Jun 12, 2025Updated last year
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆178Nov 26, 2025Updated 11 months ago
- ☆173Feb 15, 2025Updated last year
- Zeta implemantion of "Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Trans…☆12Oct 26, 2026Updated last week
- [ICLR'25] Code for KaSA, an official implementation of "KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models"☆22Jan 16, 2025Updated last year
- Work in progress.☆82Nov 25, 2025Updated 11 months ago
- hopwise: A Python Library for Explainable Recommendation based on Path Reasoning over Knowledge Graphs, ACM CIKM '25☆16Sep 30, 2026Updated last month
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆164Jul 8, 2025Updated last year
- Paper dataset for "Factored Verification: Detecting and Reducing Hallucination in Summaries of Academic Papers"☆13Oct 20, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Beyond KV Caching: Shared Attention for Efficient LLMs☆20Jul 19, 2024Updated 2 years ago
- Copyright-free Artificial Lyrics Dataset (ISMIR 2024 LBD)☆12Sep 1, 2024Updated 2 years ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆228Nov 25, 2025Updated 11 months ago
- ☆16Apr 14, 2021Updated 5 years ago
- [ACL 2024] Unveiling Linguistic Regions in Large Language Models☆34Jun 9, 2024Updated 2 years ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆356Mar 10, 2026Updated 7 months ago
- [ACL 2024 Findings] Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning☆14Sep 2, 2024Updated 2 years ago
- ☆198Jun 22, 2025Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆95Oct 22, 2024Updated 2 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.
- HW-aware training extension to AIHWKIT-Lightning for MoEs☆11Sep 18, 2025Updated last year
- [ACL 2024] Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"☆46May 24, 2024Updated 2 years ago
- Code for NeurIPS'23 paper "A Bayesian Approach To Analysing Training Data Attribution In Deep Learning"☆17Jan 12, 2024Updated 2 years ago
- ☆47Jun 14, 2026Updated 4 months ago
- Muon in Int8 Precision Made Possible☆20Jun 18, 2026Updated 4 months ago
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆46Oct 28, 2025Updated last year
- papers of llm compression☆13Mar 6, 2024Updated 2 years ago
- [ACL 2025] TokAlign: Efficient Vocabulary Adaptation via Token Alignment☆12Jun 4, 2025Updated 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.☆27Apr 21, 2025Updated last year
- 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.
- ☆13Jul 2, 2025Updated last year
- ☆19Jan 3, 2025Updated last year
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆35Jun 12, 2024Updated 2 years ago
- [ACL 2024] (Oral) LRQuant: Learnable and Robust Post-Training Quantization for Large Language Models☆12Apr 6, 2026Updated 6 months ago
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)☆35Mar 7, 2025Updated last year
- ☆22Sep 29, 2024Updated 2 years ago
- Codebase for ICML'24 paper: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs☆28Jun 25, 2024Updated 2 years ago