TensorFold v1.1.4
runtime / harness
1.1.4 makes Qwen3.8-27B's cold prompts on CUDA up to five times faster, brings Gemma 4 12B and 31B to the native CUDA engine with their drafters, lets several Flash Next streams verify their drafts in one pass on CUDA, and adds idle unload,
- Org
- ashhart
- Latest release
- v1.1.4 (2026-10-24)
- Releases in window
- 30
- Recent tags
- v1.1.4, v1.1.3, v1.0.0-beta.9, v1.1.2, v1.1.1, v1.1.0, v1.0.0-beta.8, v1.0.12
Updated 2026-10-24 · markdown