]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: fb19f94)
Tensor-parallel: Fix delayed AllReduce on Gemma-4 MoE (#22129)
authorGaurav Garg <redacted>
Mon, 20 Apr 2026 16:25:39 +0000 (21:55 +0530)
committerGitHub <redacted>
Mon, 20 Apr 2026 16:25:39 +0000 (18:25 +0200)
commitfd6ae4ca1cd5446442f6c2e5e73a2a4c9bc44993
tree62df53fbda62eb619385d11f5bc0dd3fcc22e83ftree
parentfb19f94c715c466230c72d2a32822f8a9e113708commit | diff
Tensor-parallel: Fix delayed AllReduce on Gemma-4 MoE (#22129)

* Fix delayed AllReduce on Gemma-4 MoE

Skip forward past nodes that don't consume the current one, and allow a chain of MULs.

* Check for all sources before skipping nodes

* Address review comments
ggml/src/ggml-backend-meta.cpp diff | blob | history
Packaging of ggml-org/llama.cpp