Hongqiang Wang 5f7bd9ddb9 opencl: fold the gpt-oss MoE per-expert bias adds into the epilogue (op/kernel fusion) (llama/26431) ...

* opencl: fold the gpt-oss MoE bias adds into swiglu_oai

Default on, opt out with GGML_OPENCL_FUSE_MOE_BIAS_GLU=0.

* opencl: fold the MoE down-projection bias into the combine

Default on, opt out with GGML_OPENCL_FUSE_MOE_BIAS_COMBINE=0.

2026-08-25 15:28:56 +03:00

..

cmake

cmake : add config version support (ggml/1582)

2026-08-14 22:16:06 +03:00

include

ggml: add ggml_rope_set_offset (+ metal support) (llama/27120)

2026-08-21 19:23:26 +03:00

src

opencl: fold the gpt-oss MoE per-expert bias adds into the epilogue (op/kernel fusion) (llama/26431)

2026-08-25 15:28:56 +03:00

.gitignore

…

CMakeLists.txt

ggml : bump version to 0.21.0 (ggml/1597)

2026-08-21 19:23:26 +03:00