EPISODE · Oct 3, 2025 · 4 MIN
[Gluon][Tutorial] Persistent attention by Mogball · Pull Request #7298 · triton-lang/triton
from GitHub Daily Trend · host keisuke horota
https://github.com/triton-lang/triton/pull/7298 Rewrite the attention kernel to be persistent. This gives better performance at low-contexts. However, fp16 at large context has suffered a bit due to a ptxas instruction scheduling issue in the so...
What this episode covers
https://github.com/triton-lang/triton/pull/7298 Rewrite the attention kernel to be persistent. This gives better performance at low-contexts. However, fp16 at large context has suffered a bit due to a ptxas instruction scheduling issue in the so...
NOW PLAYING
[Gluon][Tutorial] Persistent attention by Mogball · Pull Request #7298 · triton-lang/triton
No transcript for this episode yet
Similar Episodes
No similar episodes found.