Official implementation of EMNLP'23 paper "Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?"
☆24Oct 25, 2023Updated 2 years ago
Alternatives and similar repositories for llm-mixed-q
Users that are interested in llm-mixed-q are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆26Updated this week
- [FCCM 2025] Code Samples for InTAR: Inter-Task Auto-Reconfigurable Accelerator Design for High Data Volume Variation in DNNs☆15Mar 26, 2025Updated last year
- This repository contains the hardware implementation for Static BFP convolution on FPGA☆10Oct 15, 2019Updated 6 years ago
- Elana: A Simple Energy & Latency Analyzer for LLMs☆16Apr 3, 2026Updated 5 months ago
- A multicore microprocessor test harness for measuring interference☆14Apr 16, 2020Updated 6 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.
- ☆18Apr 7, 2025Updated last year
- ☆17Apr 13, 2018Updated 8 years ago
- [NeurIPS'25] FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance☆21Dec 15, 2025Updated 9 months ago
- Machine-Learning Accelerator System Exploration Tools☆204Updated this week
- ☆28Jul 2, 2026Updated 2 months ago
- c++ version of ViT☆13Nov 13, 2022Updated 3 years ago
- Shuhai is a benchmarking-memory tool that allows FPGA programmers to demystify all the underlying details of memories, e.g., HBM and DDR4…☆120Jun 15, 2025Updated last year
- Implementation of Microscaling data formats in SystemVerilog.☆34Jul 6, 2025Updated last year
- Accelerate multihead attention transformer model using HLS for FPGA☆13Dec 7, 2023Updated 2 years 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.
- bitfusion verilog implementation☆13Feb 21, 2022Updated 4 years ago
- AFPQ code implementation☆23Nov 6, 2023Updated 2 years ago
- ☆15Oct 26, 2022Updated 3 years ago
- Cross-GPU KV Cache Marketplace☆27Nov 12, 2025Updated 10 months ago
- ☆22Sep 27, 2022Updated 3 years ago
- [ISCA 2025] Official Implementation of "MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization"☆26Oct 30, 2025Updated 10 months ago
- HW Architecture-Mapping Design Space Exploration Framework for Deep Learning Accelerators☆203Jun 15, 2026Updated 3 months ago
- ☆20Mar 16, 2022Updated 4 years ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆114Oct 15, 2024Updated 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.
- DASS HLS Compiler☆30Oct 4, 2023Updated 2 years ago
- Implementation of NM sparsity recipe presented in the paper "Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers".☆11Feb 5, 2024Updated 2 years ago
- NeuraLUT-Assemble☆53Aug 20, 2025Updated last year
- An official implement of CVPR 2023 paper - NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers☆27Mar 13, 2024Updated 2 years ago
- In this repository, we explore model compression for transformer architectures via quantization. We specifically explore quantization awa…☆24May 14, 2021Updated 5 years ago
- PyTorch Implementation of MIMO (ICLR 2021)☆16Dec 16, 2022Updated 3 years ago
- Multi-branch model for concurrent execution☆18Jun 27, 2023Updated 3 years ago
- Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)☆95Jul 28, 2025Updated last year
- Official PyTorch implementation of "Learning with Memory-based Virtual Classes for Deep Metric Learning" (ICCV 2021)☆16Oct 13, 2021Updated 4 years 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.
- PolyLUT is the first quantized neural network training methodology that maps a neuron to a LUT while using multivariate polynomial functi…☆59Feb 9, 2024Updated 2 years ago
- A Vivado HLS Command Line Helper Tool☆36Oct 6, 2021Updated 4 years ago
- SAMO: Streaming Architecture Mapping Optimisation☆36Oct 4, 2023Updated 2 years ago
- A patchless architecture, based on MLP-Mixer☆18Dec 30, 2021Updated 4 years ago
- ☆10Dec 26, 2023Updated 2 years ago
- ☆11Nov 5, 2019Updated 6 years ago
- An LLVM pass to prove that an II works for the given loop for Vitis HLS☆11Aug 22, 2021Updated 5 years ago