LoreonLabsPlatform
DocsHome
  • Overview

Intelligence

  • Markets
  • Builders
  • Research
  • Ecosystems
  • Launchpads
  • Search
Builders

MathInf https://mathinf.eu/

Thomas Viehmann

Principal Research Engineer at @Lightning-AI Mathematics and Inference at @MathInf I do a lot of @PyTorch work

GitHub@ThomasViehmannWebsite
Followers
800
Public repos
51
Stars (recent)
18
Ecosystems
1

Projects

Repositories this builder owns.

dynamo
A Datacenter Scale Distributed Inference Serving Framework
—
smg
Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across SGLang, vLLM, TRT-LLM, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant auth.
—
bitsandbytes
8-bit CUDA functions for PyTorch
—
sphinx-contrib-fulltoc
Extension for Sphinx to make the sidebar show a full table of contents instead of just the local headings
—

Connected narratives

AI AgentsConsumer CryptoSocialFiStablecoinsAgent CommerceOnchain Apps

Related builders

Others building in the same ecosystem.

Jesse Pollak
— followers
0xDeployer
— followers
Xen
— followers
Ahaan Raizada
— followers
Youssef
— followers
Igor Yuzo
— followers
unsloth
5X faster 60% less memory QLoRA finetuning
—
litgpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
—
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
17
resource-stream
CUDA related news and material links
—

Recent activity

Most recently pushed work.

  • t-vi/dynamo
    pushed 13d ago
  • t-vi/smg
    pushed 19d ago
  • t-vi/bitsandbytes
    pushed 12mo ago
  • t-vi/sphinx-contrib-fulltoc
    pushed 14mo ago