Official code for paper: [CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Faster.
-
Updated
Jun 29, 2025 - Python
#
inference-efficiency
Here are 8 public repositories matching this topic...
Official repository of the paper "A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models"
-
Updated
Feb 13, 2026 - Python
[NeurIPS 2025] Official code for paper: Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs.
-
Updated
Sep 20, 2025 - Python
This is a collection of our research on efficient AI, covering hardware-aware NAS and model compression.
-
Updated
Oct 25, 2024 - Python
[ICCV 2025] Official code for paper: Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
-
Updated
Jul 1, 2025 - Python
A tutorial of model quantization using TensorFlow
machine-learning tensorflow tensorflow-lite tflite model-quantization inference-efficiency quantization-aware-training
-
Updated
Aug 2, 2021 - Python
O(N) attention with a bounded inference KV cache. D4 Daubechies wavelet field + content-gated Q·K gather at dyadic offsets.
nlp rust machine-learning deep-learning language-modeling pytorch wavelet language-model attention-mechanism wavelet-transform ablation inference-efficiency ablation-study kv-cache linear-attention efficient-attention sparse-attention wavelet-attention
-
Updated
Mar 9, 2026 - Python
🦀 The transformer is a brilliant hack scaled past its limits. DREX is what comes next — tiered memory 🧠, sparse execution ⚡, and a learned controller that knows what to remember 💾✨
rust cuda memory-efficient candle external-memory incremental-learning cognitive-architecture continual-learning catastrophic-forgetting episodic-memory inference-efficiency neural-architecture sparse-attention llm long-context tiered-memory ml-research memory-augmented transformer-alternative beyond-transformer
-
Updated
Mar 9, 2026 - Python
Improve this page
Add a description, image, and links to the inference-efficiency topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the inference-efficiency topic, visit your repo's landing page and select "manage topics."