Skip to content
View SamMausberg's full-sized avatar
3 followers · 3 following

Highlights

  • Pro

Block or report SamMausberg

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
SamMausberg/README.md

Hi, I'm Sam.

I'm a systems developer in Vancouver interested in GPU computing, AI, and mathematics.

I'm currently working on FindTensor, an experimental compiler and runtime project for LLM inference.

I enjoy understanding systems close to the hardware and care about careful benchmarking, reproducible results, and correctness.

A few things I've worked on

  • FindTensor — an ongoing exploration of compiler and runtime techniques for LLM inference.
  • Lean formalizations — formalization work in Lean 4 and mathlib around several open problems in combinatorics.
  • GPU architecture research — worked with Professor Tor Aamodt at UBC ECE on modeling newer GPU architectures in GPGPU-Sim.

Tools I've worked with

Python, Rust, C++, CUDA, PTX, NCCL, Lean 4, PyTorch, vLLM, Bazel, and Linux.

Contact

findtensor.com · LinkedIn · Email

Popular repositories Loading

  1. gpu-app-collection gpu-app-collection Public

    Forked from accel-sim/gpu-app-collection

    A repository where GPU applications are aggregated using a common build flow that supports multiple CUDA versions.

    Cuda 1

  2. gpgpu-sim_distribution gpgpu-sim_distribution Public

    Forked from accel-sim/gpgpu-sim_distribution

    GPGPU-Sim provides a detailed simulation model of a contemporary GPU running CUDA and/or OpenCL workloads and now includes an integrated (and validated) energy model, GPUWattch.

    C++

  3. Dockerfile Dockerfile Public

    Forked from accel-sim/Dockerfile

    Dockerfile

  4. lean-formalizations lean-formalizations Public

    Lean

  5. capp-vllm-bench capp-vllm-bench Public

    vLLM performance profiling of Command A+ (W4A4) on 2x H100 benchmark sweep + tuning breakdown.

    Python

  6. SamMausberg SamMausberg Public