3
Repos
7
Stars
1
Forks
0
Watchers
Repositories (3)
HunyuanOCR-ROCm
AIwork4me/HunyuanOCR-ROCm
Python
Evaluation-backed AMD ROCm port of HunyuanOCR-1.5 with reproducible OmniDocBench v1.6 benchmarks across llama.cpp, vLLM, and Transformers on gfx1100.
3
0
Muse-Glimmer-30B-ROCm
AIwork4me/Muse-Glimmer-30B-ROCm
Python
Reproducible RDNA reference for Meta Muse-Glimmer-30B — adapting MI-series ROCm recipes to Ryzen AI and Radeon with vLLM, llama.cpp, DFlash and auditable benchmarks.
3
1
Qwen3.8-27B-ROCm
AIwork4me/Qwen3.8-27B-ROCm
Python
Reproducible AMD ROCm reference for Qwen3.8-27B (gfx1151 validated): vLLM + llama.cpp dual-path, 20-cell benchmark matrix, UX-first verdicts
1
0