hjk1030

Limit engine correctness check

6

Resolves issue #54. I assume the problem appears when there are floating point errors during serialization, so I added a function to check the subset relation with floating error tolerance.

Add implementation for clearing cache table

13

Added a function to delete all the data in the cache table. Trying to resolve issue #122.

Fix inference bug when there are NULL in columns

6

The problem in issue #104 seems to be caused by having NaN in the dataframe, which is not possible to transformed into json. By replacing the NaN in the dataframe...

Test proxy score correctness

1

Resolves issue #55. Since no real index is provided for the jackson dataset, I compared the inference count when using the random proxy score and the accurate proxy score generated...

First, thank you for sharing the code for this excellent work! I'm currently reproducing your results using torch-inductor, and am particularly interested in how you collected the optimization triggering during...