locuslab / wandaLinks
A simple and effective LLM pruning approach.
☆760Updated 10 months ago
Alternatives and similar repositories for wanda
Users that are interested in wanda are comparing it to the libraries listed below
Sorting:
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆810Updated 10 months ago
- [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baich…☆1,023Updated 8 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆617Updated last year
- Official PyTorch implementation of QA-LoRA☆137Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆692Updated 10 months ago
- For releasing code related to compression methods for transformers, accompanying our publications☆431Updated 5 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,258Updated 3 months ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆819Updated last month
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,426Updated 11 months ago
- Large Context Attention☆716Updated 4 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆343Updated 7 months ago
- ☆543Updated 6 months ago
- ☆223Updated last year
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,113Updated last year
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆295Updated 3 months ago
- Explorations into some recent techniques surrounding speculative decoding☆269Updated 6 months ago
- The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction☆388Updated 11 months ago
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆371Updated last year
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆395Updated 6 months ago
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆456Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,325Updated last week
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆640Updated 11 months ago
- ☆541Updated 7 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆731Updated 8 months ago
- Codebase for Merging Language Models (ICML 2024)☆832Updated last year
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆653Updated last year
- Microsoft Automatic Mixed Precision Library☆609Updated 8 months ago
- Serving multiple LoRA finetuned LLM as one☆1,066Updated last year
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆546Updated last year
- Fast inference from large lauguage models via speculative decoding☆762Updated 10 months ago