]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
musa: enable fp16 mma (all) and cublas on qy2 (#13842)
authorR0CKSTAR <redacted>
Thu, 26 Jun 2025 04:11:59 +0000 (12:11 +0800)
committerGitHub <redacted>
Thu, 26 Jun 2025 04:11:59 +0000 (12:11 +0800)
commit716301d1b03c31875ec3b24526c48c8b1bd0fd8c
treeb5e0408499177b9c5d9ada0a175a37fe5e8d2078
parent60ef23d6c14d325d83eae5752e5de39ad268e9b0
musa: enable fp16 mma (all) and cublas on qy2 (#13842)

* musa: enable fp16 mma (all) and cublas on qy2

Signed-off-by: Xiaodong Ye <redacted>
* Update ggml/src/ggml-cuda/ggml-cuda.cu

Co-authored-by: Johannes Gäßler <redacted>
* Address review comments

Signed-off-by: Xiaodong Ye <redacted>
* Address review comments

Signed-off-by: Xiaodong Ye <redacted>
* musa: disable MUL_MAT_ID (q2_k × f32) due to precision issues

Signed-off-by: Xiaodong Ye <redacted>
---------

Signed-off-by: Xiaodong Ye <redacted>
Co-authored-by: Johannes Gäßler <redacted>
ggml/src/ggml-cuda/common.cuh
ggml/src/ggml-cuda/fattn-wmma-f16.cu
ggml/src/ggml-cuda/ggml-cuda.cu
ggml/src/ggml-musa/mudnn.cuh