[TTFS] clean interior-point kernels to improve inference #228
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
Codecov Report
@@ Coverage Diff @@
## master #228 +/- ##
==========================================
- Coverage 74.29% 74.19% -0.10%
==========================================
Files 37 38 +1
Lines 3684 3697 +13
==========================================
+ Hits 2737 2743 +6
- Misses 947 954 +7
📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
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Outdated suggestions cannot be applied.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.
@inbounds @simdin a systematic way before for loopsprint_initto ease compiler job (1s gain in itself)x-ref #186
Currently, we get on MadNLP#master:
With this PR:
(note that this is independent from the results already reported in #227 )
As a reminder, when we get
InferenceTimingNode: x/y, that means we are spendingxseconds in the LLVM compilation, andyseconds in total (compilation + precompilation). With this PR, it takes 4s to compile the call to MadNLP, 2.5s to precompile the code and do the type inference.