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:
- ☆10Oct 28, 2020Updated 5 years ago
- ☆11Sep 20, 2024Updated last year
- ☆12Mar 4, 2022Updated 3 years ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆48Jan 21, 2026Updated last month
- ☆19May 4, 2023Updated 2 years ago
- ☆20Dec 24, 2024Updated last year
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆33Aug 14, 2024Updated last year
- ☆27Jan 8, 2024Updated 2 years ago
- Code release for AdapMoE accepted by ICCAD 2024☆35Apr 28, 2025Updated 10 months ago
- Cooperative Learning of Energy-Based Model and Latent Variable Model via MCMC Teaching☆27Aug 4, 2018Updated 7 years ago
- LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation☆33Oct 11, 2025Updated 4 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆144Dec 4, 2024Updated last year
- Transformers components but in Triton☆34May 9, 2025Updated 9 months ago
- Official code for the paper "Attention as a Hypernetwork"☆48Jun 22, 2024Updated last year
- Official codebase for ICLR oral paper Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling☆36Apr 14, 2022Updated 3 years ago
- Visually Grounded PCFG Induction☆39May 18, 2022Updated 3 years ago
- [ICLR 2025] Official Code Release for Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation☆49Mar 1, 2025Updated 11 months ago
- ☆352Apr 2, 2024Updated last year
- Statistical discontinuous constituent parsing☆11Feb 15, 2018Updated 8 years ago
- POSTECH: Compiler Construction (Spring 2022)☆10Mar 10, 2023Updated 2 years ago
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆57Nov 20, 2024Updated last year
- ☆20May 24, 2025Updated 9 months ago
- Training project about Deep Learing☆12Jun 22, 2017Updated 8 years ago
- Learning Descriptor Networks for 3D Shape Synthesis and Analysis☆35Feb 15, 2022Updated 4 years ago
- Generic library for neural collapse and several derivative works on the phenomenon.☆18Apr 14, 2025Updated 10 months ago
- Repository for the DPP'23 course☆11May 2, 2024Updated last year
- Graph-based Dependency Parser☆46Jan 25, 2016Updated 10 years ago
- ☆52Jun 10, 2024Updated last year
- SparseGPT + GPTQ Compression of LLMs like LLaMa, OPT, Pythia☆42Mar 13, 2023Updated 2 years ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆277Aug 31, 2024Updated last year
- KAF : Kolmogorov-Arnold Fourier Networks☆20Feb 19, 2025Updated last year
- Chameleon: A MatMul-Free TCN Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data☆25Jun 6, 2025Updated 8 months ago
- [ICML'24 Oral] APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference☆47Jun 4, 2024Updated last year
- source code for NAACL2022 main conference "Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs"☆10Sep 26, 2022Updated 3 years ago
- Integration test of Verilog AXI modules (https://github.com/alexforencich/verilog-axi) with LiteX.☆17Dec 19, 2022Updated 3 years ago
- ☆11Oct 11, 2023Updated 2 years ago
- Parallel Self-Adjusting Computation☆15Jul 5, 2021Updated 4 years ago
- U-Net neural network applied to FWI problems☆12Dec 8, 2022Updated 3 years ago
- ☆11Oct 13, 2019Updated 6 years ago