joennlae / halutmatmul
Hashed Lookup Table based Matrix Multiplication (halutmatmul) - Stella Nera accelerator
☆209Updated last year
Alternatives and similar repositories for halutmatmul:
Users that are interested in halutmatmul are comparing it to the libraries listed below
- Algebraic enhancements for GEMM & AI accelerators☆273Updated 3 weeks ago
- A thin, highly portable toolkit for efficiently compiling dense loop-based computation.☆148Updated 2 years ago
- Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024☆177Updated 11 months ago
- Exploring the scalable matrix extension of the Apple M4 processor☆168Updated 4 months ago
- High-Performance SGEMM on CUDA devices☆86Updated 2 months ago
- This project aims to enable language model inference on FPGAs, supporting AI applications in edge devices and environments with limited r…☆150Updated 10 months ago
- An implementation of bucketMul LLM inference☆215Updated 8 months ago
- Code sample showing how to run and benchmark models on Qualcomm's Window PCs☆95Updated 5 months ago
- throwaway GPT inference☆140Updated 9 months ago
- Run 64-bit Linux on LiteX + RocketChip☆193Updated 7 months ago
- Open source machine learning accelerators☆374Updated 11 months ago
- ☆242Updated last year
- Tiny ASIC implementation for "The Era of 1-bit LLMs All Large Language Models are in 1.58 Bits" matrix multiplication unit☆121Updated 11 months ago
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆250Updated last year
- A Data-Centric Compiler for Machine Learning☆82Updated last year
- Nvidia Instruction Set Specification Generator☆253Updated 8 months ago
- A library for incremental loading of large PyTorch checkpoints☆56Updated 2 years ago
- ☆87Updated last year
- ☆290Updated this week
- A description of Minotaur can be found in https://arxiv.org/abs/2306.00229.☆103Updated 7 months ago
- A C++ to Verilog translation tool with some basic guarantees that your code will work.☆166Updated last month
- DiscoGrad - automatically differentiate across conditional branches in C++ programs☆204Updated 6 months ago
- An open-source efficient deep learning framework/compiler, written in python.☆690Updated 3 weeks ago
- Sequential Logic☆111Updated last week
- IREE's PyTorch Frontend, based on Torch Dynamo.☆72Updated this week
- Fearless hardware design☆176Updated this week
- VSCode LLVM Compiler Explorer☆229Updated 9 months ago
- ☆253Updated last year
- The Finite Field Assembly Programming Language☆35Updated this week
- Fork of LLVM to support AMD AIEngine processors☆128Updated this week