[Compilation] GDN decode cold kernel compilation time is too long on SM90/100/120/121
#4.110 geöffnet am 23.07.2026
Repository-Metriken
- Stars
- (5.756 Sterne)
- PR-Merge-Metriken
- (Durchschn. Merge 11T 23h) (186 gemergte PRs in 30 T)
Beschreibung
Noticed by @bkryu : "In our recent CI telemetry, we have been seeing that tests/gdn/test_decode_delta_rule.py runs very long (30-50 mins on every arch) and has been straining our CI.
TL;DR of the cause: the reference and kernels are all fine. Most time is spent on cold kernel compilation. On a B200 I locally see ~800 cases that collapses to ~200 cute.compile calls based on the cache key logic.
For some kernels, B/tile_v/T/cache flags/pool-strides each key a new compile. Would be great if we can make the kernels batch and/or seqlen dynamic to systematically reduce unit testing time."