Commit 3ef13a3
authored
add cuda benchmark ci (#15883)
Summary: Introduce cuda benchmark ci for monitoring cuda backend
performance.
the ci will run on three situations:
1. it will run all possible models (voxtral, gemma and whisper) combine
with all possible quantization schema on every day's 1am pst;
2. it will run an random model everytime a PR got merged;
3. manually tirggered by user.
Differential Revision: D874005611 parent 9e7e17c commit 3ef13a3
File tree
6 files changed
+1459
-540
lines changed- .ci/scripts
- .github
- scripts
- workflows
- backends/cuda
- tests
6 files changed
+1459
-540
lines changed
0 commit comments