A foundational model (GLM5.2, kimi k3, etc) inference engine for the AMD Strix Halo APU (gfx1151) — Rust + tokio streaming, HIP/ROCm compute.
4
stars
199
commits
Rust
primary language
Sep 10, 2026
updated
199 commits
LCAI-TIHU/SW
LCAI-TIHU SW is a software stack of the AI inference processor based on RISC-V
23
nvidia/Kimodo-SMPLX-RP-v1
22
xynexus/hipfire
RDNA-native LLM inference engine in Rust.
2
warpfront/hipfire
613
tensorforger/FluxRT
Real-time stream editing pipeline powered by the FLUX.2-klein-4B model, optimized for consumer GPUs
445
shisa-ai/hipEngine
72
NVIDIA/TensorRT-Model-Connect
From PyTorch model to end-to-end TensorRT inference experience in two commands—AI-native,…
236
kyuz0/amd-strix-halo-toolboxes
1,889
81.7%
Python
7.3%
HIP
6.4%
Shell
3.2%
C++
1.5%
