Cpu cache for unload - #507
Draft
brycehenson wants to merge 24 commits into
Draft
Conversation
added 12 commits
August 17, 2026 04:26
…o-FastAPI into cpu_cache_for_unload # Conflicts: # README.md # api/src/core/config.py # api/src/inference/model_manager.py # api/tests/test_model_unload.py # docker/gpu/docker-compose.yml # docs/configuration.md
Reduce load speed, or reduce load time? I don't understand why reducing load speed would be a good thing. |
Centralize request timeout accounting into ModelManager.hold(). Use it for generate_from_phonemes(). Remove MODEL_AUTO_UNLOAD_ENABLED. Replace it with MODEL_AUTO_UNLOAD_TIMEOUT_SECONDS=0 is the default/off state.
… config.py inline comment on allow_dev_unload
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
adds a unload strategy which moves the model weights to cpu ram. This substantially speeds up reload.
default is "destroy" which reloads from disk
Benchmark
RTX 2070 SUPER with PCIe Gen3 x4 link
depends on #506 which should go in first