MiniMax-H3: flash attention in the video VAE, faster tile stitching, ggml-cuda speed patch by danielhanchen · Pull Request #17 · unslothai/stable-diffusion.cpp · GitHub
Skip to content

MiniMax-H3: flash attention in the video VAE, faster tile stitching, ggml-cuda speed patch - #17

Merged
oobabooga merged 5 commits into
masterfrom
perf/h3-gguf-speed
Oct 9, 2026
Merged

MiniMax-H3: flash attention in the video VAE, faster tile stitching, ggml-cuda speed patch#17
oobabooga merged 5 commits into
masterfrom
perf/h3-gguf-speed

Commits

  1. Commits on Oct 1, 2026

  2. Commits on Oct 8, 2026

  3. Commits on Oct 9, 2026