llama.cpp/ggml/src/ggml-musa
R0CKSTAR 716301d1b0
musa: enable fp16 mma (all) and cublas on qy2 (#13842)
* musa: enable fp16 mma (all) and cublas on qy2

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* Update ggml/src/ggml-cuda/ggml-cuda.cu

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Address review comments

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* Address review comments

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* musa: disable MUL_MAT_ID (q2_k × f32) due to precision issues

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2025-06-26 12:11:59 +08:00
..
CMakeLists.txt musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy (#13647) 2025-05-21 09:58:49 +08:00
mudnn.cu musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy (#13647) 2025-05-21 09:58:49 +08:00
mudnn.cuh musa: enable fp16 mma (all) and cublas on qy2 (#13842) 2025-06-26 12:11:59 +08:00