Daniel Hiltgen e823bff873 gemma4: enable flash attention (#15378) ...

Backport GGML kernels so we can enable flash attention for the gemma 4 model on
Metal and CUDA.

2026-04-07 08:12:36 -07:00

..

ggml

gemma4: enable flash attention (#15378)

2026-04-07 08:12:36 -07:00

gguf

Reapply "feat: incremental gguf parser (#10822)" (#11114) (#11119)

2025-06-20 11:11:40 -07:00

util/bufioutil

next ollama runner (#7913)

2025-02-13 16:31:21 -08:00

config.go

Add experimental MLX backend and engine with imagegen support (#13648)

2026-01-08 16:18:59 -08:00