Rework batcher for a reservation system #1183
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
rsuderman
force-pushed
the
reserved_batcher
branch
from
5e5f99e to
81bb5a3
Compare
With decode the majority of future steps are known a groupable. Created a basic reservation system so that steps can be reserved and the continuous batcher knows that a future groupable request is coming. This should be adapted to include grouping multiple responses, and having a "grouping" exist. E.g. multiple parallel requests in flight and grouped together for the multiple hypothesis case.
rsuderman
force-pushed
the
reserved_batcher
branch
from
8934474 to
4f96917
Compare
stbaione
reviewed
Mar 31, 2025
...hon/shortfin_apps/llm/components/token_selection_strategy/greedy_token_selection_strategy.py
Show resolved
Hide resolved
stbaione
reviewed
Mar 31, 2025
stbaione
approved these changes
Mar 31, 2025
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Outdated suggestions cannot be applied.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.
With decode the majority of future steps are known a groupable. Created a basic reservation system so that steps can be reserved and the continuous batcher knows that a future groupable request is coming.
This should be adapted to include grouping multiple responses, and having a "grouping" exist. E.g. multiple parallel requests in flight and grouped together for the multiple hypothesis case.