]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 7b95ea5)
ggml-webgpu: Fix bug in FlashAttention support check (#22492)
authorReese Levine <redacted>
Wed, 29 Apr 2026 07:59:00 +0000 (00:59 -0700)
committerGitHub <redacted>
Wed, 29 Apr 2026 07:59:00 +0000 (10:59 +0300)
commitd6a5094004d5be6e404220d2e799daa348739a96
tree57d792c543b3b21ac859ac6761563a5fa4dbd94ctree
parent7b95ea5d110241cf8b0fb6936927387f63f18a32commit | diff
ggml-webgpu: Fix bug in FlashAttention support check (#22492)

* Fix flashattention support check for devices that don't support subgroups

* set path to none if kv_tile doesn't fit
ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp diff | blob | history
ggml/src/ggml-webgpu/ggml-webgpu.cpp diff | blob | history
Packaging of ggml-org/llama.cpp