Skip to content
This repository was archived by the owner on Sep 10, 2025. It is now read-only.

Update import of sdpa_with_kv_cache to custom_ops #1470

Merged
merged 1 commit into from
Jan 22, 2025
+1 −1
Merged

Update import of sdpa_with_kv_cache to custom_ops #1470

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion torchchat/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1025,7 +1025,7 @@ def apply_rotary_emb(x: Tensor, freqs_cis: Tensor) -> Tensor:
# For quantized_decomposed ops
from executorch.kernels import quantized # no-qa
# For llama::sdpa_with_kv_cache.out, preprocess ops
from executorch.extension.llm.custom_ops import sdpa_with_kv_cache # no-qa
from executorch.extension.llm.custom_ops import custom_ops # no-qa

class PTEModel(nn.Module):
def __init__(self, config, path) -> None:
Expand Down
Loading