TranslatedUsing dense-compute cards to accelerate sparse, large-VRAM hosts, where the hosts include AI Max+ 395, M3 512G, DGX Spark, and others.
- llama-cpp
- pipeline-parallelism
- prefill-decode
- rtx-3060
47,133 repositories indexed
1–3 of 3 · Most stars
TranslatedUsing dense-compute cards to accelerate sparse, large-VRAM hosts, where the hosts include AI Max+ 395, M3 512G, DGX Spark, and others.
TranslatedZongzhu (宗主, "sect leader"): a Grok Bot voice terminal on the Waveshare 1.75C round-screen ESP32, with blinking eye expressions, subtitles and spoken readout, including firmware and backend source code (2.5.2.9)
Vulkan-based implementation of 3Dfx Glide for Linux / Wine, spun off from DXVK.