]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
vulkan: use a more appropriate amount of threads when generating shaders (llama/16418)
authorEve <redacted>
Sat, 4 Oct 2025 20:04:27 +0000 (20:04 +0000)
committerGeorgi Gerganov <redacted>
Sun, 12 Oct 2025 08:16:23 +0000 (11:16 +0300)
commit2ca8fa37fa6708f890c1b0e3d520cd4e8cfb645d
tree18252ab460d90cf2dbcc601238482f1b79744e0e
parent93882335a8a0b3435869d1d47b506dfccea9d044
vulkan: use a more appropriate amount of threads when generating shaders (llama/16418)

* use a more flexible amount of threads

* fix windows compile and 0 thread case

* nominmax
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp