Stars
Python tool for converting files and office documents to Markdown.
Diffusion on syntax trees for program synthesis
A reading list for SRAM-based Compute-In-Memory (CIM) research.
A systolic array simulator for multi-cycle MACs and varying-byte words, with the paper accepted to HPCA 2022.
Repository to host and maintain scale-sim-v2 code
Fast and accurate DRAM power and energy estimation tool
HeteroHalide: From Image Processing DSL to Efficient FPGA Acceleration
Differentiable Combinatorial Scheduling at Scale (ICML'24). Mingju Liu, Yingjie Li, Jiaqi Yin, Zhiru Zhang, Cunxi Yu.
an API and runtime environment for data processing with MapReduce for shared-memory multi-core & multiprocessor systems.
A library for efficient similarity search and clustering of dense vectors.
Benchmarks of approximate nearest neighbor libraries in Python
DHLS (Dynamic High-Level Synthesis) compiler based on MLIR
The homepage of OneBit model quantization framework.
Simple and SCM-friendly KiCad file parser based on Python dataclasses for KiCad 6.0 and up.
TiledCUDA is a highly efficient kernel template library designed to elevate CUDA C’s level of abstraction for processing tiles.
Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"
RL_PCB is a novel learning-based method for optimising the placement of circuit components on a Printed Circuit Board (PCB).
Torchhd is a Python library for Hyperdimensional Computing and Vector Symbolic Architectures
BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.
Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA