Add optimization_level to TTConfig for vLLM compile #2663
Merged
Conversation
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
odjuricicTT
requested review from
AleksKnezevic,
acicovicTT,
ajakovljevicTT,
jameszianxuTT,
kmabeeTT,
ljovanovicTT,
mmanzoorTT,
mrakitaTT,
ndrakulicTT,
sdjukicTT,
sgligorijevicTT and
vzeljkovicTT
as code owners
odjuricicTT
force-pushed
the
odjuricic/vllm-optimization-level
branch
from
f81d5b2 to
b8ec277
Compare
odjuricicTT
requested review from
acolicTT,
nvukobratTT and
pilkicTT
as code owners
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #2663 +/- ##
=======================================
Coverage 28.51% 28.51%
=======================================
Files 31 31
Lines 4075 4075
=======================================
Hits 1162 1162
Misses 2913 2913 ☔ View full report in Codecov by Sentry. |
odjuricicTT
force-pushed
the
odjuricic/vllm-optimization-level
branch
2 times, most recently
from
c9eac9c to
4043be2
Compare
mmanzoorTT
approved these changes
Dec 23, 2025
tests/integrations/vllm_plugin/pooling/test_batched_inference.py
Outdated
Show resolved
Hide resolved
- Add optimization_level field to TTConfig with default value 0 - Propagate optimization_level through get_pjrt_compile_config() - Set optimization_level = 1 for Qwen models in batched inference test
odjuricicTT
force-pushed
the
odjuricic/vllm-optimization-level
branch
from
4043be2 to
af5f45b
Compare
mmanzoorTT
approved these changes
Dec 29, 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Outdated suggestions cannot be applied.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.
Ticket
N/A
Problem description
The vLLM plugin needed support for configuring the tt-mlir optimization level through TTConfig, similar to how
enable_const_evalis propagated.What's changed
optimization_levelfield toTTConfigdataclass with default value of 0optimization_levelthroughget_pjrt_compile_config()totorch_xla.set_custom_compile_options()optimization_level = 1for Qwen models in the batched inference pooling testChecklist