]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
Override SSM_A op for Qwen3 Next to reduce splits (#17587)
authorPiotr Wilkin (ilintar) <redacted>
Mon, 1 Dec 2025 23:43:13 +0000 (00:43 +0100)
committerGitHub <redacted>
Mon, 1 Dec 2025 23:43:13 +0000 (00:43 +0100)
commit746f9ee88941c2f259268c484fe8278375387081
tree9b5004a8cc08011ddad75af648ed988829490ebd
parent9810cb82476e605bef45f9c51009c9989873ff89
Override SSM_A op for Qwen3 Next to reduce splits (#17587)

* Override SSM_A op for Qwen3 Next to reduce splits

* New tensor mapping SSM_A_NOSCAN for SSM_A used outside of OP_SSM_SCAN context.

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <redacted>
* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <redacted>
---------

Co-authored-by: Sigbjørn Skjæret <redacted>
src/llama-arch.cpp
src/llama-arch.h
src/llama-model.cpp