Relax lora string test#19312
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19312
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
| The answer is: 12<|im_end|>" | ||
| EXPECTED_QUANT_LORA_ALTERNATE_PREFIX=" | ||
| <|im_start|>user Calculate 15% of 80?<|im_end|><|im_start|>assistant | ||
| To calculate 15% of 80, we can multiply 80 by 15/100. |
There was a problem hiding this comment.
we could cut the prefix to here to avoid having two prefixes?
Seeing small numerical flakeyness causing diverging output. The output is roughly equivalent though. Current thought is different cpu architectures causing different xnnpack kernels to trigger causing minor difference in output.