Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its efficiency gain.
☆21Sep 10, 2024Updated last year
Alternatives and similar repositories for Sirius
Users that are interested in Sirius are comparing it to the libraries listed below
Sorting:
- Vortex: A Flexible and Efficient Sparse Attention Framework☆49Jan 21, 2026Updated 2 months ago
- ☆11Sep 20, 2024Updated last year
- ☆10Oct 28, 2020Updated 5 years ago
- Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.☆61Jan 30, 2025Updated last year
- ☆19May 4, 2023Updated 2 years ago
- ☆12Mar 4, 2022Updated 4 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
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆96Feb 6, 2024Updated 2 years ago
- Hardware and software implementation of Sparsely-active SNNs☆22Mar 6, 2026Updated 2 weeks ago
- [NeurIPS 2025] Multipole Attention for Efficient Long Context Reasoning☆22Dec 5, 2025Updated 3 months ago
- Open Source Projects from Pallas Lab☆21Oct 10, 2021Updated 4 years ago
- ☆17Jun 11, 2025Updated 9 months ago
- [ACL 2025] Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models☆35Nov 4, 2025Updated 4 months ago
- Cooperative Learning of Energy-Based Model and Latent Variable Model via MCMC Teaching☆27Aug 4, 2018Updated 7 years ago
- ☆19Dec 24, 2024Updated last year
- A canonical source of GenAI energy benchmark and meausrements☆50Nov 29, 2025Updated 3 months ago
- ☆27Jan 8, 2024Updated 2 years ago
- ☆63Jun 12, 2025Updated 9 months ago
- Understand what physics/algorithms do transformers learn internally when trained on planetary motion☆39Feb 9, 2026Updated last month
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆144Dec 4, 2024Updated last year
- ☆17Mar 13, 2022Updated 4 years ago
- Official implementation of the paper: "A deeper look at depth pruning of LLMs"☆15Jul 24, 2024Updated last year
- Code release for AdapMoE accepted by ICCAD 2024☆36Apr 28, 2025Updated 10 months ago
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆34Aug 14, 2024Updated last year
- rules for writing and typesetting☆25Oct 1, 2021Updated 4 years ago
- ☆18Oct 26, 2024Updated last year
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆16Jul 10, 2025Updated 8 months ago
- ☆353Apr 2, 2024Updated last year
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆57Nov 20, 2024Updated last year
- Official code for Guiding Language Model Math Reasoning with Planning Tokens☆18Feb 29, 2024Updated 2 years ago
- AIM: Accelerating Arbitrary-precision Integer Multiplication on Heterogeneous Reconfigurable Computing Platform Versal ACAP (Full Paper a…☆26May 18, 2025Updated 10 months ago
- ☆21Feb 5, 2024Updated 2 years ago
- Learning Descriptor Networks for 3D Shape Synthesis and Analysis☆35Feb 15, 2022Updated 4 years ago
- [CVPR 2025] OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts☆17Apr 2, 2025Updated 11 months ago
- LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation☆33Feb 26, 2026Updated 3 weeks ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆251Dec 16, 2024Updated last year
- Transformers components but in Triton☆34May 9, 2025Updated 10 months ago
- A comprehensive list of papers about Large-Language-Diffusion-Models.☆61Mar 2, 2026Updated 2 weeks ago
- Official repository for ICLR 2025 paper "Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs"☆16Mar 18, 2025Updated last year