feat: support for batching ('n_iter') #95
Merged
Conversation
This file contains 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
|
Latest commit should fix #99 |
fix: avoid crashing on faulted gens feat: take n_iter into account on queue calc fix: stop multi-process inference on working batches feat: avoid spamming logs about pausing inference fix: handle when image_result is None fix: remove reference to old vars feat: old model-stats.py fix: retry on submit timeout fix: avoid posting about blocking processes if there's no queue fix: use latest hordlib/sdk in pre-commit mypy hook fix: linting and submit retry tasks fix: submit exit on fault fix: forgot to clear submit_tasks feat: send back batch_index test: fix hordelib/sdk pins for pre-commit
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Outdated suggestions cannot be applied.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.
Supercedes #77
Closes
n_itersupport #24Uses the latest version of hordelib (see diff), which includes:
bridgeDataoption has been added,civitai_api_token, allowing workers to download login-gated LoRas/TIs (where the author requires a valid civitai login in order to download that model).Closes asyncio timeout on submit can put the worker into maintenance #99 by catching more exceptions from the aiohttp client. (09a070f)
This PR relies on:
See also:
n_iterin comfyui) AI-Horde#301