]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
CUDA: fix bug in rms_norm fusion (llama/15660)
authorAman Gupta <redacted>
Fri, 29 Aug 2025 13:30:06 +0000 (21:30 +0800)
committerGeorgi Gerganov <redacted>
Sat, 20 Sep 2025 10:42:44 +0000 (13:42 +0300)
commit82ce91e7d287594a56655ca880798f8b6666aef9
tree24347b28a885fa6e2a921d4ff9feaf1fd7442d9d
parent6d7ddaf793b1b9b467ca57bd415d438b321c4ea9
CUDA: fix bug in rms_norm fusion (llama/15660)

* CUDA: fix bug in rms_norm fusion

* Fix bug for OP_REPEAT

* Fix index for add
ggml/src/ggml-cuda/binbcast.cu
ggml/src/ggml-cuda/ggml-cuda.cu
ggml/src/ggml-cuda/norm.cu