Segmentation fault with torch.compile in torchchat #126669
Labels
module: aotinductor
aot inductor
needs reproduction
Someone else needs to try reproducing the issue given the instructions. No action needed from user
oncall: pt2
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
馃悰 Describe the bug
https://github.com/pytorch/torchchat/actions/runs/9154013584/job/25163857442?pr=824
Average tokens/sec: 38.80
Memory used: 0.00 GB
Using device=cpu AMD EPYC 7R32
Loading model...
Time to load model: 0.02 seconds
/exec: line 35: 4135 Segmentation fault python generate.py --checkpoint-path ${MODEL_PATH} --device cpu --dtype ${DTYPE} --temperature 1.0 --sequential-prefill --compile
Versions
Pytorch CI
cc @ezyang @msaroufim @bdhirsh @anijain2305 @chauhang @desertfire @chenyang78
The text was updated successfully, but these errors were encountered: