Lockless and ordered, parallel chain reaction processing
-
Updated
Dec 28, 2022 - C++
#
threadripper
Here are 9 public repositories matching this topic...
MojoLlama is a high-throughput inference engine for CPU, built on Modular MAX. GGUF native, MoE-optimized, with support for 50+ architectures — from Llama to Gemma 4 to hybrid SSM models. GPU acceleration via MAX engine for supported models.
-
Updated
May 24, 2026 - Python
Ryzentosh - Hackintosh based on TRX40-E and Threadripper 3960x
-
Updated
Jun 19, 2025 - ASL
Not a product. Not a framework. Nothing here is packaged for you to deploy. This is my house, my desk, my power bill, and the machine that thinks in it. It exists so I can point at something on my wall and say that box runs my world.
benchmark ai inference devbox asr threadripper huggingface benchmarkin litellm rtx-5090 rtx-5080 threadripper-pro
-
Updated
Oct 11, 2026 - Lua
AMD rcraid Linux 6.14 DKMS port, NVMe RAID0 setup, mdadm/XFS tuning and fio benchmarks for high-speed workstation storage.
-
Updated
Jul 4, 2026 - Shell
A build log for one workstation: a 284B mixture-of-experts model across two GPUs and 256 GB of RAM, measured.
threadripper mixture-of-experts llama-cpp local-llm gguf speculative-decoding deepseek ik-llama-cpp moe-offloading
-
Updated
Oct 21, 2026 - Python
Aims to fix low FPS in Unity games on high core count CPUs (AMD Threadripper). Valheim mod (BepInEx) that keeps the game on one chiplet: one-chiplet affinity measured +20% on a Threadripper 3970X. Open research: help map which CPUs it helps.
performance unity fps amd unity3d multithreading ryzen threadripper bepinex epyc cpu-affinity game-performance valheim valheim-mod chiplet bepinex-plugin timberborn high-core-count
-
Updated
Oct 20, 2026 - C#
Threadripper optomized XMR mining program
-
Updated
Sep 18, 2026 - Python
Add this topic to your repo
To associate your repository with the threadripper topic, visit your repo's landing page and select "manage topics."