Enable fast GPU inference of large language models that exceed GPU memory by managing memory dynamically.
-
Updated
Mar 30, 2026 - Rust
Enable fast GPU inference of large language models that exceed GPU memory by managing memory dynamically.
64-bit RISC CPU Architecture
RISC-V CPU emulator developed in C++. Supports instruction decoding, disassembly, and execution with a simple memory model. Includes test binaries (CRC32, MD5, hello world) to validate behavior and explore low-level computer architecture concepts.
Kite: Architecture Simulator for RISC-V Instruction Set
Built custom assembly language and Assembler for my custom-built Computing Machinery project as its software extension. Mapped machine-functionality to assembly capable of data-control, machine-control and temporal-control operations and Implemented an assembler with syntax and semantic analysis 💻.
Air.rs 70B+ inference on consumer GPU, LLM inference in Rust
CPU INFOrmation library (x86/x86-64/ARM/ARM64, Linux/Windows/Android/macOS/iOS)
AirLLM 70B inference with single 4GB GPU
CPU design - part of new 72-series
Stack Based Virtual Machine in Golang
🚀 Optimize memory for large language models, enabling 70B models on a 4GB GPU and 405B Llama3.1 on 8GB VRAM without compression techniques.
📚 Access comprehensive materials for the NYU Computing Systems Architecture course, including lectures, assignments, and exams from Fall 2025.
This repository contains all the lecture slides, homeworks, Mid Terms, and the final project of the Computing Systems Architectures course by Prof. Azeez Bhavnagarwala, in Fall 2025 at NYU.
💻 An assembler for custom, user-defined instruction sets! https://hlorenzi.github.io/customasm/web/
Makine Öğrenmesi Kod Kütüphanesi
fasm68k - Motorola 68000 instruction set for fasmg (flat assembler g)
An x86/x64 instruction disassembler written in C
Add a description, image, and links to the instruction-set topic page so that developers can more easily learn about it.
To associate your repository with the instruction-set topic, visit your repo's landing page and select "manage topics."