Open
Conversation
Remove ambiguity with RunPod's {"input": ...} HTTP wrapping by renaming
the input_data parameter to payload in 13 Python files (19 functions)
and 5 documentation files. Also fix a local variable shadowing issue in
cpu_burst_ready by renaming its internal payload variable to serialized.
- Add .flash/ directory to gitignore across getting_started examples - Add __main__ test block to mixed_workers pipeline.py
Output of /analyze-repos: adds module structure, public API surface, cross-repo dependencies, code health assessment, and test strategy.
Five scaling strategies across GPU (scale-to-zero, always-on, high-throughput) and CPU (scale-to-zero, burst-ready) with load test script for observing scaling behavior. Includes cost analysis and configuration reference in README.
All QB endpoint URLs used the wrong path segment. The flash-generated routes use /runsync, not /run_sync.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
04_scaling_performance/01_autoscaling/) with 5 scaling strategies: GPU scale-to-zero, always-on, high-throughput, and CPU scale-to-zero, burst-ready.flash/to gitignores and test block topipeline.pyTest plan
flash rundiscovers all 5 new@remoteendpoints in01_autoscaling/python gpu_worker.pyandpython cpu_worker.pydirectly to confirm test blocks workpython load_test.py --helpto verify CLI args parse correctly04_scaling_performance/README.mdflash runfrom repo root