Cleanup codebase: removed unnecessary code/logic #298
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
Qubitium
changed the title
Qubitium
changed the title
|
@merrymercy @hnyls2002 PR tested with no performance regression. Ready for review/merge. |
Qubitium
changed the title
Qubitium
force-pushed
the
mod-forward-sleep
branch
from
ca73c5f
to
e56ce1b
Compare
|
Latest commit removed redundant math: prompt_tokens = len(req.input_ids). So adding len(req.input_ids) - prompt_tokens is always 0.
|
Qubitium
changed the title
Qubitium
changed the title
|
Latest commit : 9472363 Removed unused ReqState.lock |
merrymercy
requested changes
Mar 22, 2024
|
|
||
| await asyncio.sleep(0.0006) | ||
| if not slept: | ||
| await asyncio.sleep(0.0006) |
There was a problem hiding this comment.
- Did you find this give better performance?
- @hnyls2002 please also take a look
There was a problem hiding this comment.
- In my limited testing with low concurrency (1-2 concurrent requests with range 1-10 batches each) I did not find performance diff.
But this is unnecessary code/logic. There is no need to sleep for another 0.6ms (causing potential thread context switch) when it has slept for 30ms in earlier condition extend_dependency_time: float = 0.03.
Qubitium
force-pushed
the
mod-forward-sleep
branch
from
9472363
to
c68572f
Compare
Qubitium
force-pushed
the
mod-forward-sleep
branch
from
c68572f
to
ad6410b
Compare
Qubitium
force-pushed
the
mod-forward-sleep
branch
from
ad6410b
to
431cbb8
Compare
merrymercy
approved these changes
Mar 23, 2024
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Outdated suggestions cannot be applied.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.
Fixed two issues in router loop:
Cleanup:
self.eos_token_idin modle_rpcEDIT:
Reverted due to review: (removed useless math for calculating # of completion_tokens)