]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 66d8ecc)
vulkan: remove the need for the dryrun (#16826)
authorJeff Bolz <redacted>
Tue, 4 Nov 2025 19:28:17 +0000 (13:28 -0600)
committerGitHub <redacted>
Tue, 4 Nov 2025 19:28:17 +0000 (13:28 -0600)
commitad51c0a720062a04349c779aae301ad65ca4c856
tree300fd5647a69bb174e7c2c332640b4cafff1676ctree
parent66d8eccd42b5b5b2179c60a6d41376d3917f3b40commit | diff
vulkan: remove the need for the dryrun (#16826)

* vulkan: remove the need for the dryrun

Allocate pipelines and descriptor sets when requested.

Reallocate the prealloc buffers when needed, and flush any pending work
before reallocating.

For rms_partials and total_mul_mat_bytes, use the sizes computed the last time
the graph was executed.

* remove dryrun parameters
ggml/src/ggml-vulkan/ggml-vulkan.cpp diff | blob | history
Packaging of ggml-org/llama.cpp