]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: cb14b06)
vulkan: fix push constant size for quantize_q8_1 (#18687)
authorJeff Bolz <redacted>
Thu, 8 Jan 2026 14:40:58 +0000 (08:40 -0600)
committerGitHub <redacted>
Thu, 8 Jan 2026 14:40:58 +0000 (15:40 +0100)
commit2524c2616458c7d6ee62fa4b4fa17e5091833544
tree8309621e0fc60154240ecdc1f4bdc4501f3b1b61tree
parentcb14b069955f12992f6c47be98a061f23ea13cf5commit | diff
vulkan: fix push constant size for quantize_q8_1 (#18687)

I added an assert to catch further mismatches, and it found several.
Fix those, too.
ggml/src/ggml-vulkan/ggml-vulkan.cpp diff | blob | history
Packaging of ggml-org/llama.cpp