Vulkan Use Mmap (disable Vulkan MMap opt out)#14525
Draft
inforithmics wants to merge 1 commit intoollama:mainfrom
Draft
Vulkan Use Mmap (disable Vulkan MMap opt out)#14525inforithmics wants to merge 1 commit intoollama:mainfrom
inforithmics wants to merge 1 commit intoollama:mainfrom
Conversation
4 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Vulkan Use Mmap (disable Vulkan MMAp opt out)
Draft until new Vendor sync because in newer llama.cpp Versions mmap works without problems in Vulkan (It shows that it uses more memory but in reality it doesn't) It shows more used memory in Process and gpu but in effect there is more free memory.
The reason it seems that the Memory is duplicated is that the Shared Memory used in the GPU is also reported to be used by ollama (But it is the same memory) So for example 6GB Shared Memory used Ollama although "uses" 6GB Memory. This hapens on iGPU where the shared Memory is used for GPU offload.