Repository navigation
Apply saved performance profiles to model launch settings - #444
Open
smshagor-dev wants to merge 7 commits into
Open
smshagor-dev wants to merge 7 commits into
smshagor-dev wants to merge 7 commits into
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
The Advanced settings performance selector previously persisted
Auto,Eco,Balanced,PerformanceandMaximumwithout using the value to configure model inference. The backend always planned with Auto.Model launch preview, activation, and streaming chat now read the saved performance selection and use the same hardware-aware planner. Eco reduces threads, RAM/VRAM budgets, GPU layers, batch size and context; Balanced limits resources conservatively; Performance increases bounded CPU concurrency; and Maximum uses available logical CPU cores and larger batch sizes. GPU offload and context still respect device, RAM and dedicated VRAM headroom, and CPU-only machines stay CPU-only.
Advanced Settings now shows the effective saved profile and CPU threads, refreshing those values after saving. Invalid profile values are rejected on save; previously persisted unknown values fall back to Auto for safe inference.
Regression tests cover each named profile on CPU-only and GPU machines, plus bounded offload and low-memory context planning.
Fixes #338.