[ICML 2026] Official implementation of "FOCUS: DLLMs Know How to Tame Their Compute Bound".
☆20Aug 2, 2026Updated 3 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:
- A training-free framework that accelerates diffusion language models through dynamic cache eviction and sparse attention☆30Oct 16, 2025Updated last year
- A programmable distributed training system for PyTorch☆27Sep 22, 2026Updated last month
- ☆13Mar 26, 2026Updated 7 months ago
- SplitBud is a Split Learning framework built upon Flower☆14Mar 22, 2025Updated last year
- gpuFI-4 is a detailed microarchitecture-level fault injection framework to assess the cross-layer vulnerability of hardware structures an…☆11Apr 18, 2022Updated 4 years 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.
- This repository contains the code for the ICLR 2026 paper “DASH: Deterministic Attention Scheduling for High-Throughput Reproducible LLM …☆15Jun 23, 2026Updated 4 months ago
- Nano vLLM☆11Feb 26, 2026Updated 8 months ago
- [ASPLOS'25] Towards End-to-End Optimization of LLM-based Applications with Ayo☆80Mar 11, 2026Updated 8 months ago
- ☆19May 27, 2026Updated 5 months ago
- ☆15Nov 7, 2026Updated last week
- Official implementation of "DPad: Efficient Diffusion Language Models with Suffix Dropout"☆67Feb 13, 2026Updated 9 months ago
- The repository for ATC'25 paper "Greyhound: Hunting Fail-Slows in Hybrid-Parallel Training at Scale"☆19Sep 7, 2026Updated 2 months ago
- Artifact for paper: ZipMoE☆18May 28, 2026Updated 5 months ago
- Algorithm-System Co-design: accurate and efficient 2-bit KV cache quantization for LLM Inference.☆25May 20, 2026Updated 5 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- [HPCA 2022] GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Design☆39Mar 30, 2022Updated 4 years ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 2025Updated last year
- [ASPLOS' 26] TetriServe: Efficiently Serving Mixed DiT Workloads☆20Mar 12, 2026Updated 8 months ago
- [ICLR 2026 🔥] Official pytorch implementation for "Attention Is All You Need for KV Cache in Diffusion LLMs"☆43Jul 13, 2026Updated 4 months ago
- [DAC 2026] FlashFPS☆17Jun 1, 2026Updated 5 months ago
- codebase for Coruscant: Co-Designing GPU Kernel and Sparse Tensor Core to Advocate Unstructured Sparsity in Efficient LLM Inference☆11Oct 17, 2025Updated last year
- [NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.☆20Mar 30, 2026Updated 7 months ago
- ☆25Nov 11, 2026Updated last week
- Dirigent: Lightweight Serverless Orchestration☆46Aug 26, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Flexible and Pluggable Serving Engine for Diffusion LLMs☆158Jul 13, 2026Updated 4 months ago
- Neural Network accelerator powered by MVUs and RISC-V.☆13Jul 21, 2024Updated 2 years ago
- Prompt structures and examples used in "Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach"☆12Nov 17, 2024Updated 2 years ago
- extractlinks GO package for extracting anchor links from HTML☆11Dec 4, 2019Updated 6 years ago
- [ICML 2026] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆36Sep 12, 2025Updated last year
- This is the repository containing the implementation of sparse dense matrix multiplication for the matrix dimension of 560 x 560.☆10Jul 7, 2021Updated 5 years ago
- ☆13Nov 13, 2025Updated last year
- A toy simulator for multi-chiplet GPU☆26Apr 16, 2026Updated 7 months ago
- ☆16Nov 30, 2022Updated 3 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- This is Official implementation for T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasonin…☆25Mar 5, 2026Updated 8 months ago
- ☆10Aug 3, 2022Updated 4 years ago
- Disaggregated Prefill-Decode LLM serving engine on mini-sglang with a proved KV page state machine (PdLedger)☆23Nov 11, 2026Updated last week
- ICCD'24 paper: "AutoVCoder: A systematic framework for automated verilog code generation"☆28Dec 17, 2024Updated last year
- ☆10Nov 20, 2024Updated last year
- ☆93Oct 17, 2025Updated last year
- ☆20Jun 4, 2026Updated 5 months ago
Are these results useful?