Daniel Hiltgen bd6c1d6b49 flash attn: add auto mode for llama engine (#13052) ... * flash attn: add auto mode for llama engine If the user does not specify fa in the environment, use auto-mode. * review comments * ensure kv cache quantized types have FA explicitly enabled additional review comments		2025-12-12 13:27:19 -08:00
..
cache.go	refactor: use the built-in max/min to simplify the code (#12280)	2025-09-16 17:14:21 -07:00
cache_test.go	Runner for Ollama engine	2025-02-13 17:09:26 -08:00
image.go	Llama cpp bump (df1b612): granite docling / mamba2 optimizations / multimodal encoding fixes (#12552)	2025-10-13 15:26:18 -07:00
image_test.go	Llama cpp bump (df1b612): granite docling / mamba2 optimizations / multimodal encoding fixes (#12552)	2025-10-13 15:26:18 -07:00
runner.go	flash attn: add auto mode for llama engine (#13052)	2025-12-12 13:27:19 -08:00