]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: bcf5bda)
vulkan: Update topk_moe fusion to handle gpt's late softmax (#16656)
authorJeff Bolz <redacted>
Wed, 29 Oct 2025 13:44:29 +0000 (08:44 -0500)
committerGitHub <redacted>
Wed, 29 Oct 2025 13:44:29 +0000 (14:44 +0100)
commit10fcc41290e233788f5a4215314156e8e023eb92
tree40bb5da33c31e35db69695af8b89fe0a781b87c5tree
parentbcf5bda6f5df559565d11d7c8e8295c1159a85eccommit | diff
vulkan: Update topk_moe fusion to handle gpt's late softmax (#16656)

* vulkan: Update topk_moe fusion to handle gpt's late softmax

Based on #16649.

* Add ggml_check_edges

* Add sync logging to show fusion effects

* handle clamp added in #16655

* Update ggml/src/ggml-impl.h

Co-authored-by: Diego Devesa <redacted>
ggml/src/ggml-impl.h diff | blob | history
ggml/src/ggml-vulkan/ggml-vulkan.cpp diff | blob | history
ggml/src/ggml-vulkan/vulkan-shaders/topk_moe.comp diff | blob | history
Packaging of ggml-org/llama.cpp