[HPCA 2026 Best Paper Candidate] Official implementation of "Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models"
☆66Feb 8, 2026Updated 8 months ago
Alternatives and similar repositories for Focus
Users that are interested in Focus are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [HPCA 2026] FractalCloud: A Fractal-Inspired Architecture for Efficient Large-Scale Point Cloud Processing☆22Apr 21, 2026Updated 5 months ago
- [DAC 2026] FlashFPS☆16Jun 1, 2026Updated 4 months ago
- ☆19Nov 11, 2024Updated last year
- The official implementation of HPCA 2025 paper, Prosperity: Accelerating Spiking Neural Networks via Product Sparsity☆43Aug 9, 2025Updated last year
- This is Official implementation for T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasonin…☆24Mar 5, 2026Updated 7 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆161Jul 19, 2025Updated last year
- [ASPLOS 2026] M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization.☆17Jan 29, 2026Updated 8 months ago
- H2-LLM: Hardware-Dataflow Co-Exploration for Heterogeneous Hybrid-Bonding-based Low-Batch LLM Inference☆121Apr 26, 2025Updated last year
- ☆124Nov 17, 2023Updated 2 years ago
- A bit-level sparsity-awared multiply-accumulate process element.☆21Jul 9, 2024Updated 2 years ago
- [ICML 2025] CoreMatching: Co-adaptive Sparse Inference Framework for Comprehensive Acceleration of Vision Language Model☆16May 27, 2025Updated last year
- Repo for SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting (ISCA25)☆75Apr 25, 2025Updated last year
- [ACM MM 2026 Oral]⚡ZEUS accelerates your diffuser. Any modality. Any model. Any scheduler. https://yixiao-wang-stats.github.io/zeus/☆22Jun 2, 2026Updated 4 months ago
- MICRO 2024 Evaluation Artifact for FuseMax☆19Aug 26, 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.
- Official implementation of "DPad: Efficient Diffusion Language Models with Suffix Dropout"☆66Feb 13, 2026Updated 7 months ago
- ☆167Jun 24, 2024Updated 2 years ago
- ☆40Aug 27, 2025Updated last year
- ☆41Oct 21, 2025Updated 11 months ago
- [AAAI 2026] Official implementation of "FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models". If you find this reposi…☆19Aug 26, 2026Updated last month
- ☆27Apr 3, 2026Updated 6 months ago
- Torch2Chip (MLSys, 2024)☆56Apr 2, 2025Updated last year
- An efficient spatial accelerator enabling hybrid sparse attention mechanisms for long sequences☆33Mar 7, 2024Updated 2 years ago
- ☆38Jul 27, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Model LLM inference on single-core dataflow accelerators☆22Dec 16, 2025Updated 9 months ago
- ☆18Sep 30, 2026Updated last week
- ☆30Feb 27, 2025Updated last year
- This is the official Python version of CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Act…☆20Oct 25, 2024Updated last year
- LoAS: Fully Temporal-Parallel Dataflow for Dual-Sparse Spiking Neural Networks, MICRO 2024.☆21Mar 19, 2025Updated last year
- [DATE'23] The official code for paper <CLAP: Locality Aware and Parallel Triangle Counting with Content Addressable Memory>☆24Updated this week
- ☆70Oct 14, 2025Updated 11 months ago
- AFPQ code implementation☆23Nov 6, 2023Updated 2 years ago
- ASIC simulation of Multi-ported Memory Module. And it can offer SRAM-based dual-port basic building block to support multiple read/write …☆25May 30, 2016Updated 10 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.
- Artifact for paper "PIM is All You Need: A CXL-Enabled GPU-Free System for LLM Inference", ASPLOS 2025☆148Aug 22, 2026Updated last month
- ☆50Apr 8, 2023Updated 3 years ago
- ☆49Apr 22, 2021Updated 5 years ago
- HippoMM: Hippocampal-inspired Multimodal Memory☆21May 22, 2025Updated last year
- [ICML 2026]A framework to compare low-bit integer and float-point formats☆84May 6, 2026Updated 5 months ago
- Some Hardware Architectures for GEMM☆296May 22, 2025Updated last year
- ☆35Dec 22, 2025Updated 9 months ago