[ExecuTorch][llm] Add numerical kernel tests for quantized_moe_ffn#21123
[ExecuTorch][llm] Add numerical kernel tests for quantized_moe_ffn#21123digantdesai wants to merge 4 commits into
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21123
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 1 Unrelated FailureAs of commit aa32a34 with merge base bfed808 ( NEW FAILURE - The following job has failed:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
Stack from ghstack (oldest at bottom):
Add TestQuantizedMoeFfnOp: 5 tests comparing custom op output against
a Python q-dq reference (sigmoid+bias, sigmoid no-bias, softmax,
single-token, route_scale=0.0).
Differential Revision: D102381999