feat(llm): add QMD_FORCE_CUDA env var to disable Vulkan offloading#338
Open
JasonOA888 wants to merge 1 commit intotobi:mainfrom
Open
feat(llm): add QMD_FORCE_CUDA env var to disable Vulkan offloading#338JasonOA888 wants to merge 1 commit intotobi:mainfrom
JasonOA888 wants to merge 1 commit intotobi:mainfrom
Conversation
On Windows VMs with para-virtualized GPUs, QMD may use Vulkan offloading instead of pure CUDA mode even when CUDA is available. This adds QMD_FORCE_CUDA env var to force CUDA and disable Vulkan: export QMD_FORCE_CUDA=1 qmd query "test" Fixes tobi#278
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
On Windows VMs with para-virtualized GPUs (e.g., ExHyperV RTX 4090), QMD may use Vulkan offloading instead of pure CUDA mode even when CUDA is working correctly:
Solution
Add
QMD_FORCE_CUDAenvironment variable to force CUDA and disable Vulkan:This sets
gpu: "cuda"ingetLlama()options, bypassing the auto-detection that might choose Vulkan.Related
QMD_FORCE_CPUfor older GPUs (Force cpu run on older nvidia architecture (e.g. Pascal) #299)Fixes #278