Lucas Liebenwein
|
be916b19e0
|
feat: [AutoDeploy] unfusing attention for native support (#3668)
* [AutoDeploy] unfused streamlined attention + caching
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
* improved unit testing
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
* reviewer feedback
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
* some updates to attn_mask handling
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
* updated manual benchmarking and cudagraph capture
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
---------
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
|
2025-05-02 09:06:49 +08:00 |
|