Michael Yang 59412fbb43 convert(gptoss): mxfp4 to ggml layout to avoid jit conversion (#12018) ...

* convert: return bytes written

* ggml flavor mxfp4

* simplify jit conversion

* comment

2025-08-26 16:41:02 -07:00

..

backend

convert(gptoss): mxfp4 to ggml layout to avoid jit conversion (#12018)

2025-08-26 16:41:02 -07:00

nn

update vendored llama.cpp and ggml (#11823)

2025-08-14 14:42:58 -07:00

backend.go

kvcache: Use Cast instead of Copy for flash attention masks

2025-08-19 12:36:28 -07:00