[ACL 2026 Findings] Living repository for the survey paper “Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects”.
☆32Oct 20, 2026Updated this week
Alternatives and similar repositories for Efficient-LVLMs-Inference
Users that are interested in Efficient-LVLMs-Inference are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ACL 2026 Main] See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video …☆32Jul 4, 2026Updated 3 months ago
- ☆19Feb 18, 2025Updated last year
- ☆35Nov 18, 2025Updated 11 months ago
- [EMNLP 2025 Main] SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning☆50Apr 16, 2026Updated 6 months ago
- Rookie's guide☆15Aug 10, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆14Jan 27, 2026Updated 8 months ago
- MMSpec: Benchmarking Speculative Decoding for Vision-Language Models☆45Jul 2, 2026Updated 3 months ago
- [ICLR 2026] Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models☆31Mar 21, 2026Updated 7 months ago
- Implementation for paper "Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models".☆139May 17, 2026Updated 5 months ago
- ☆12Sep 26, 2025Updated last year
- The Official Implementation of Ada-KV [NeurIPS 2025]☆141Nov 26, 2025Updated 10 months ago
- ☆17Mar 24, 2025Updated last year
- 利用QT可视化编程实现停车场管理系统☆10Jan 22, 2019Updated 7 years ago
- ☆11Sep 27, 2022Updated 4 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆39Mar 9, 2026Updated 7 months ago
- Experiments with representation engineering☆14Feb 28, 2024Updated 2 years ago
- ☆36Jun 3, 2025Updated last year
- [ICCV 2025] SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs☆90Jan 17, 2026Updated 9 months ago
- ☆34Mar 5, 2026Updated 7 months ago
- ☆34Mar 12, 2026Updated 7 months ago
- ERGO (Efficient Reasoning & Guided Observation) is a large vision-language model trained with reinforcement learning on efficiency object…☆19Feb 25, 2026Updated 8 months ago
- Myers Research Group's official webpage☆15Oct 15, 2026Updated last week
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification☆33Mar 30, 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.
- [ACL 25] The Low-cost Long Context Understanding Benchmark for Large Language Models (Outstanding Paper Award)☆23Jul 30, 2025Updated last year
- [NeurIPS 25] InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding☆25Jan 25, 2026Updated 9 months ago
- [CVPR2026] VecAttention: Vector-wise Sparse Attention for Accelerating Long-Context Inference☆22Oct 17, 2026Updated last week
- The official implementation for SETA (TIP 2024).☆12Feb 17, 2025Updated last year
- [AAAI 26'] This is the official pytorch implementation for paper: Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acc…☆46Nov 13, 2025Updated 11 months ago
- [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆227Feb 11, 2026Updated 8 months ago
- ☆14Mar 11, 2026Updated 7 months ago
- Official repo for "Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge" ICLR2025☆114Mar 14, 2025Updated last year
- This repo contains evaluation code for the paper "Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency"☆11May 12, 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.
- [ICLR'25] Streaming Video Question-Answering with In-context Video KV-Cache Retrieval☆130Nov 4, 2025Updated 11 months ago
- PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence☆36Updated this week
- [Neurips’25] Code for the paper "Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization"☆32Sep 25, 2025Updated last year
- [EMNLP'26] Code and data for VTCBench, a VLM benchmark for long-context understanding capabilities under vision-text compression paradigm…☆28Aug 27, 2026Updated last month
- [EMNLP Main 2026]VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning.☆26Jul 20, 2026Updated 3 months ago
- [ICLR 2025🔥] D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models☆27Jul 7, 2025Updated last year
- [NeurIPS 2025] Official Implementation of ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding.☆72Jan 28, 2026Updated 8 months ago