Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its efficiency gain.
☆22Sep 10, 2024Updated 2 years ago
Alternatives and similar repositories for Sirius
Users that are interested in Sirius are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆10Oct 28, 2020Updated 6 years ago
- A rejection-sampling based distribution alignment method for extreme actor-policy mismatch RL Training☆14Feb 11, 2026Updated 9 months ago
- ☆17Jun 15, 2026Updated 5 months ago
- ☆19May 4, 2023Updated 3 years 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
- 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.
- codebase for MUSTAFAR:Promoting Unstructured Sparsity for KV Pruning in LLM Inference☆12Nov 6, 2025Updated last year
- Area, energy, and latency models for hardware components☆13Jun 22, 2026Updated 4 months ago
- SketchSSM: Write to the Full State, Read from a Compact Sketch☆16Oct 12, 2026Updated last month
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆99Feb 6, 2024Updated 2 years ago
- SCARIF is a tool to estimate the embodied carbon emissions of data center servers with accelerator hardware (GPUs, FPGAs, etc.)☆15Updated this week
- ☆64May 4, 2024Updated 2 years ago
- ☆17Jun 11, 2025Updated last year
- Soft-QMIX: Integrating Maximum Entropy For Monotonic Value Function Factorization☆16Jul 3, 2024Updated 2 years ago
- Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.☆77Oct 23, 2026Updated 3 weeks 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.
- ☆365Apr 2, 2024Updated 2 years ago
- ☆27Jan 8, 2024Updated 2 years ago
- ☆20Dec 24, 2024Updated last year
- A canonical source of GenAI energy benchmark and meausrements☆50Nov 29, 2025Updated 11 months ago
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆69Aug 22, 2026Updated 2 months ago
- Open Source Projects from Pallas Lab☆21Oct 10, 2021Updated 5 years ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆280Aug 31, 2024Updated 2 years ago
- Accelerator RTL inspired by VEGETA [HPCA'23] and MicroScopiQ [ISCA'25]☆17Nov 11, 2025Updated last year
- Sparsity as a Variance Regulator for Improved Depth Utilization in Language Models☆16May 11, 2026Updated 6 months 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 PyTorch implementation of the paper "Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Princ…☆47Jul 18, 2025Updated last year
- Training project about Deep Learing☆12Jun 22, 2017Updated 9 years ago
- Official implementation of the paper: "A deeper look at depth pruning of LLMs"☆15Jul 24, 2024Updated 2 years ago
- ☆22Feb 5, 2024Updated 2 years ago
- Code release for AdapMoE accepted by ICCAD 2024☆40Apr 28, 2025Updated last year
- ☆66Jun 12, 2025Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆162Dec 4, 2024Updated last year
- Code for the paper "Refining Language Model with Compositional Explanation" (NeurIPS 2021)☆11Oct 25, 2021Updated 5 years ago
- PyTorch Implementation of Weakly Supervised Pre-training - [IJCAI19]☆12May 23, 2020Updated 6 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.
- ☆18Mar 13, 2022Updated 4 years ago
- Official code for AAAI'20 paper "Merging Weak and Active Supervision for Semantic Parsing"☆11Dec 8, 2022Updated 3 years ago
- A high-throughput LLM serving engine with non-uniform KV cache compression, built on vLLM☆16Nov 9, 2026Updated last week
- CVPR 2021 Oral Paper PatchGenCN☆11Oct 28, 2021Updated 5 years ago
- LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation☆37Feb 26, 2026Updated 8 months ago
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆36Aug 14, 2024Updated 2 years ago
- An extended project of the LLM Compiler paper, focusing on developing LLM-based Autonomous Agents.☆26Oct 22, 2024Updated 2 years ago
Are these results useful?