A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends

Stealth LLM inference engine

A transformers library in the Nim programming language

Search more, hallucinate less - a suite of MCP servers and CLI tools to supercharge your LLM skillset

GLM-5.3-Flash 2x RTX Pro 6000 on vLLM + EXL3 for 1~2M Fp8 KV context

Qwen3.8-Flash-Next optimized for 1x RTX Pro 6000

Keep an eye on vLLM inference engine

Keep an eye on SGLang LLM inference engine

Constantine: modular, high-performance, zero-dependency cryptography stack for verifiable computation, proof systems and blockchain protocols.

An educational raytracer

LLM Ops related artifacts (Dockerfile, Podman scripts, Kubernetes for high performance LLM serving and frontends)

LLM quantization scripts

A latency and fairness optimized threadpool. Tuned for async IO and decent for compute tasks.

Accédez à l'ensemble des textes consolidés de la législation française, en local, avec recherche textuelle, sémantique et hybrides avancées

Exploration of Project Euler in Lean 4 language

A state-of-the-art multithreading runtime: message-passing based, fast, scalable, ultra-low overhead

The HPC toolbox: fused matrix multiplication, convolution, data-parallel strided tensor primitives, OpenMP facilities, SIMD, JIT Assembler, CPU detection, state-of-the-art vectorized BLAS for float…

A repo of my talks

A Nim wrapper for CLBlast, a tuned OpenCL BLAS library

Loop efficiently over a variadic number of containers