Memory usage tests were run in T339890#9155985, T339890#9156601, T339890#9159257, and T339890#9162780. The 4th test where float was downcasted to np.float32 and numpy arrays preprocessed, resulted in a 5x drop in memory usage. This was the best result of the 4 tests performed.
In this task we will work on adapting the recommendation-api to fetch and use the float32 preprocessed numpy arrays from swift.
| Project | Branch | Lines +/- | Subject | |
|---|---|---|---|---|
| research/recommendation-api | master | +81 -50 | Load preprocessed numpy arrays from swift |
| Status | Subtype | Assigned | Task | ||
|---|---|---|---|---|---|
| Open | None | T296994 Observations from research study for Section Translation on Thai Wikipedia | |||
| Open | DAbad | T293648 Content Translation Recommendations API | |||
| Open | kevinbazira | T308164 Migrate Content Translation Recommendation API to Lift Wing | |||
| Open | kevinbazira | T339890 Host the recommendation-api container on LiftWing | |||
| Open | kevinbazira | T346218 Adapt the recommendation-api to use float32 preprocessed numpy arrays from swift | |||
| Open | kevinbazira | T346411 Upload recommendation-api preprocessed numpy binaries to Swift |
Change 956846 had a related patch set uploaded (by Kevin Bazira; author: Kevin Bazira):
[research/recommendation-api@master] Load preprocessed numpy arrays from swift
Change 956846 merged by jenkins-bot:
[research/recommendation-api@master] Load preprocessed numpy arrays from swift