A few tweaks to the JetStream code for better observability and throu… #158
+134
−15
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
fenghuizhang
force-pushed
the
fhzhang/rampup
branch
8 times, most recently
from
62aa6c5 to
bda2e22
Compare
|
Thanks Fenghui for the change! LGTM. |
benchmarks/benchmark_serving.py
Outdated
| self._init_value = init_value | ||
| self._value = init_value | ||
| self._block_on_zero_seconds = block_on_zero_seconds | ||
| self._lock = asyncio.Lock() |
There was a problem hiding this comment.
The lock seems not needed, as there isn't any thread or coroutine switch when read/write self._value (operation to self._value is atomic).
There was a problem hiding this comment.
Good to know. Thanks. I removed the lock and renamed things accordingly. Did a manual run, things look fine.
…ghput. + Added custom GC config on the serve side, by defult Python does too much GC as we allocate a lot of objects. + Tweaked log level in orchestrator to WARNING so important messages don't hide in server logs. + Added slow TTFT detection and text logging on both server and client side (benchmark_serving as the client). + Fixed timestamp recording on the server side. + Added prefill based throttling on the client side. + Added concurrent active request throttling on the client side.
fenghuizhang
force-pushed
the
fhzhang/rampup
branch
from
bda2e22 to
231acc8
Compare
wyzhang
approved these changes
Jan 3, 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Outdated suggestions cannot be applied.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.
…ghput.