wkljohn/ds4-strix-halo-tp-odinlink

Strixfold: DeepSeek-V4.1-Flash on two AMD Strix Halo boxes over USB4. A HIP backend and Strix Halo kernels for TensorFold.

llama.cpp modified to work with Strix Halo + dGPU as an accelerator, Dual Strix Halo Machines, or both

A deterministic inference engine for DeepSeek-V4.1-Flash 1017 and Qwen3.8-Flash-Next on a single AMD Strix Halo 128 GB

Working recipe to serve DeepSeek-V4-Flash across two NVIDIA DGX Spark (GB10) nodes with vLLM (TP=2, FP8 KV, MTP) over a RoCE/RDMA link — Docker image, launch scripts, RDMA/NCCL setup, and the gotchas.

Rust LLM inference engine tuned for AMD Strix Halo (gfx1151): a fork of Strata with ggml/llama.cpp-derived HIP kernels. Five models on one 128 GB machine.

LLM inference in C/C++

Native DeepSeek V4.1 Flash inference across one RTX PRO 6000 and four DGX Spark expert workers