Jesse Gross 29ddfc2cab ggml: Disable flash attention for gemma2 ... Our new engine implementation of gemma2 doesn't support flash attention, which means that it also doesn't support KV cache quantization. Currently, it is possible to turn these two on, which will result in a crash.		2025-09-10 16:40:45 -07:00
..
ggml.go	ggml: Disable flash attention for gemma2	2025-09-10 16:40:45 -07:00
ggml_test.go	ggml: fix crash for array head counts	2025-04-27 11:38:06 -07:00
gguf.go	convert: fix tensor sorting (#12015)	2025-08-26 13:57:46 -07:00
gguf_test.go	convert: fix tensor sorting (#12015)	2025-08-26 13:57:46 -07:00
type.go	convert(gptoss): mxfp4 to ggml layout to avoid jit conversion (#12018)	2025-08-26 16:41:02 -07:00