Native HIP/C++ Z-Image-Turbo inference optimized for AMD Radeon RX 7900 XTX gfx1100 WMMA.
-
Updated
Aug 5, 2026 - C++
#
rx7900xtx
Here are 4 public repositories matching this topic...
Device-native Qwen3-TTS inference for AMD RX 7900 XTX and NVIDIA RTX 4090 with explicit HIP/CUDA kernels, streaming and Resident execution.
text-to-speech amd gpu cuda inference nvidia tts speech-synthesis low-latency hip rocm qwen rtx4090 qwen3-tts rx7900xtx
-
Updated
Aug 13, 2026 - C++
⚡ Automated nightly builds & portable releases for lucebox (DFlash) inference server on NVIDIA CUDA (sm_75-120) and AMD ROCm 7 (Strix Halo gfx1151, RX 7900 XTX gfx1100, R9700 gfx1201) with zero-dependency $ORIGIN RPATH bundling.
cuda hip rocm nightly-builds ai-inference llm-inference gfx1100 rdna3 deepseek-v3 rtx5090 rdna4 strix-halo gfx1151 gfx1201 deepseek-v4 dflash lucebox rx7900xtx rocm-7 portable-binaries
-
Updated
Sep 2, 2026 - Python
Run Qwen3-TTS 12Hz models natively on 24GB AMD RX 7900 XTX or NVIDIA RTX 4090 GPUs with minimal latency.
text-to-speech amd gpu cuda inference nvidia tts speech-synthesis low-latency hip rocm qwen rtx4090 qwen3-tts rx7900xtx
-
Updated
Sep 3, 2026 - C++
Add this topic to your repo
To associate your repository with the rx7900xtx topic, visit your repo's landing page and select "manage topics."