#
Starred repositories
Multi-core HW accelerator mapping optimization framework for layer-fused ML workloads.
Brevitas: neural network quantization in PyTorch
An application-focused API for memory management on NUMA & GPU architectures
A schematic editor for VLSI/Asic/Analog custom designs, netlist backends for VHDL, Spice and Verilog. The tool is focused on hierarchy and parametric designs, to maximize circuit reuse.
The next generation of OpenLane, rewritten from scratch with a modular architecture
A PULP SoC for education, easy to understand and extend with a full flow for a physical design.
Collaborative documentation for and from Jean Zay users. Official Jean Zay documentation: https://www.idris.fr/eng/jean-zay/
Implementation of SYCL and C++ standard parallelism for CPUs and GPUs from all vendors: The independent, community-driven compiler for C++-based heterogeneous programming models. Lets applications …
A lightweight library for portable low-level GPU computation using WebGPU.
C++ wrappers for SIMD intrinsics and parallelized, optimized mathematical functions (SSE, AVX, AVX512, NEON, SVE))
A heterogeneous accelerator-centric compute cluster
A retargetable MLIR-based machine learning compiler and runtime toolkit.
HW Architecture-Mapping Design Space Exploration Framework for Deep Learning Accelerators
PyTorch emulation library for Microscaling (MX)-compatible data formats
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
IREE's PyTorch Frontend, based on Torch Dynamo.
Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.
Summarize existing representative LLMs text datasets.
Adding quality checks and confounds computation steps to fmriprep for stroke data.