Pinned Loading

1. snu-mllab/GuidedQuant snu-mllab/GuidedQuant Public

   Official PyTorch implementation of "GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance" (ICML 2025)

   Python 45 1

2. snu-mllab/LayerMerge snu-mllab/LayerMerge Public

   Official PyTorch implementation of "LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging" (ICML 2024)

   Python 30 1

3. snu-mllab/Efficient-CNN-Depth-Compression snu-mllab/Efficient-CNN-Depth-Compression Public

   Official PyTorch implementation of "Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming" (ICML'23)

   Python 13

4. snu-mllab/KVzip snu-mllab/KVzip Public

   [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)

   Python 125 7

5. snu-mllab/Efficient-Dataset-Condensation snu-mllab/Efficient-Dataset-Condensation Public

   Official PyTorch implementation of "Dataset Condensation via Efficient Synthetic-Data Parameterization" (ICML'22)

   Python 113 14

6. ruikangliu/FlatQuant ruikangliu/FlatQuant Public

   [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"

   Python 179 20