]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
overview / pkg / ggml / sources / whisper.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 63a767a)
Vulkan Shader Refactor, Memory Debugging Option (llama/7947)
author0cc4m <redacted>
Sun, 16 Jun 2024 05:17:31 +0000 (07:17 +0200)
committerGeorgi Gerganov <redacted>
Tue, 18 Jun 2024 06:39:40 +0000 (09:39 +0300)
commit922971041b45ea6ae9b6166089a194b00aa4e50a
tree362bfc62431f8cc9760fd1eded7b5a0f60ae8866tree
parent63a767a1340dbdabbf8dfbc8773800208f5f1b72commit | diff
Vulkan Shader Refactor, Memory Debugging Option (llama/7947)

* Refactor shaders, extract GLSL code from ggml_vk_generate_shaders.py into vulkan-shaders directory

* Improve debug log code

* Add memory debug output option

* Fix flake8

* Fix unnecessary high llama-3 VRAM use
ggml-vulkan.cpp diff | blob | history
Packaging of ggerganov/whisper.cpp