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
..
ggml.go	flash attn: add auto mode for llama engine (#13052)	2025-12-12 13:27:19 -08:00
ggml_test.go	ggml: fix crash for array head counts	2025-04-27 11:38:06 -07:00
gguf.go	fs/ggml: write int32 and int64 values to gguf files (#13335)	2025-12-07 21:49:14 -08:00
gguf_test.go	fs/ggml: write int32 and int64 values to gguf files (#13335)	2025-12-07 21:49:14 -08:00
type.go	fs/ggml: fix function name in comment (#12630)	2025-10-15 21:53:38 -07:00