Code for data-aware compression of DeepSeek models
☆72Dec 11, 2025Updated 5 months ago
Alternatives and similar repositories for MoE-Quant
Users that are interested in MoE-Quant are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Work in progress.☆80Nov 25, 2025Updated 5 months ago
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆395Feb 14, 2025Updated last year
- ☆112Feb 26, 2026Updated 2 months ago
- Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)☆90Jul 28, 2025Updated 9 months ago
- ☆16Sep 27, 2023Updated 2 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.
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆155Aug 21, 2025Updated 9 months ago
- LLM Inference with Microscaling Format☆34Nov 12, 2024Updated last year
- Official code for the paper "Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark"☆30Jun 30, 2025Updated 10 months ago
- Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)☆45Feb 13, 2024Updated 2 years ago
- ☆21Apr 27, 2026Updated 3 weeks ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆180Nov 11, 2025Updated 6 months ago
- IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse☆101Mar 14, 2026Updated 2 months ago
- Fast and memory-efficient exact attention☆21Apr 10, 2026Updated last month
- ☆37Aug 7, 2025Updated 9 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆89Jan 23, 2025Updated last year
- This repository contains the training code of ParetoQ introduced in our work "ParetoQ Scaling Laws in Extremely Low-bit LLM Quantization"☆124Oct 15, 2025Updated 7 months ago
- Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024☆186Apr 16, 2024Updated 2 years ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆321Mar 10, 2026Updated 2 months ago
- ☆143Aug 18, 2025Updated 9 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆81Aug 12, 2024Updated last year
- [ICLR 2025, IEEE TPAMI 2026] Mixture Compressor & MC#☆73Feb 12, 2025Updated last year
- ☆12Oct 17, 2023Updated 2 years ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,076Sep 4, 2024Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆216Nov 25, 2025Updated 5 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆96Sep 4, 2024Updated last year
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆280Nov 3, 2023Updated 2 years ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆168Oct 13, 2025Updated 7 months ago
- The official implementation of Bi-Mamba☆16Oct 22, 2025Updated 6 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆280Updated this week
- ☆21Dec 30, 2022Updated 3 years ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆24Oct 5, 2024Updated last year
- ☆66Apr 26, 2025Updated last year
- 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 the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆51Oct 21, 2023Updated 2 years ago
- Code accompanying the NeurIPS 2020 paper: WoodFisher (Singh & Alistarh, 2020)☆53Mar 8, 2021Updated 5 years ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆391Apr 13, 2025Updated last year
- ☆10Nov 16, 2024Updated last year
- An implementation of LazyLLM token pruning for LLaMa 2 model family.☆13Jan 6, 2025Updated last year
- ☆12Aug 22, 2023Updated 2 years ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆838Mar 6, 2025Updated last year