Periodic concurrency mode #411
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
…workflow (#401) * Implement periodic concurrency manager/worker and inference profiler workflow * Address feedback * Address feedback
* Add macros to reuse it for checking range options * Add tests for periodic-concurrency-range option * Add periodic-concurrency-range and request-period options * Add doc for periodic-concurrency-range and request-period * Add test for request-period option * Revert macro and add reusable test function * Add more tests * Small refactor * Refactor a subcase * Require bi-directional gRPC streaming for periodic concurrency mode * Address feedback * Refine the error message * Add bi-directional gRPC streaming options for periodic concurrency mode * Add request-parameter option and refactor * Refactor * Add valid case for request-parameter option * Add --request-parameter doc and edit periodic concurrency description * Custom request parameter is currently only supported by gRPC * Parse and store the type of request parameter * Add checks between act vs. exp * Remove uint type and rebase * Change doc * Minor fix * Address feedback
* Initial draft * Small edit * Add note * Address feedback * Minor fix
…n infinite loop (#403) * Throw exception when request period larger than max tokens rather than infinite loop * Update periodic_concurrency_worker.cc
* Initial parameter passing support * Fix parameter ordering * Remove commented code * Remove unnecessary type in request parameter * Fix includes and map assignment * Update grpc request parameters to use only strings in PA
* Add continus batch size benchmark to LLM guide * Update llm.md * Update llm.md
nv-hwoo
approved these changes
Oct 7, 2023
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.
Epic branch. Already tested. Just merging into main.