]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 7781e5f)
vulkan: Better thread-safety for command pools/buffers (#14116)
authorJeff Bolz <redacted>
Wed, 11 Jun 2025 14:48:52 +0000 (09:48 -0500)
committerGitHub <redacted>
Wed, 11 Jun 2025 14:48:52 +0000 (09:48 -0500)
commitbd248d4dc7265437e1918dc53ae3f49a0c592e5f
tree4132de0ae975bce75441a0802f5e1cc75966c41ctree
parent7781e5fe99f2a4fc1c8af0a8488eedac4644cb72commit | diff
vulkan: Better thread-safety for command pools/buffers (#14116)

This change moves the command pool/buffer tracking into a vk_command_pool
structure. There are two instances per context (for compute+transfer) and
two instances per device for operations that don't go through a context.
This should prevent separate contexts from stomping on each other.
ggml/src/ggml-vulkan/ggml-vulkan.cpp diff | blob | history
Packaging of ggml-org/llama.cpp