Skip to content

fix(wan-audio): restore the phase argument at the three multi-line _apply_rope_with_cache_range call sites #1460

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Anai-Guo wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(wan-audio): restore the phase argument at the three multi-line _apply_rope_with_cache_range call sites #1460

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
3 changes: 3 additions & 0 deletions lightx2v/models/networks/wan/infer/audio/transformer_infer.py
100755 → 100644
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -404,6 +404,7 @@ def infer_self_attn_with_kvcache(self, phase, grid_sizes, x, seq_lens, freqs, sh
attn_v = kv_cache.v_cache(self.block_idx, attn_start, local_end_idx)
if use_local_cache_rope:
attn_k = self._apply_rope_with_cache_range(
phase,
attn_k,
freqs,
h,
Expand Down Expand Up @@ -432,6 +433,7 @@ def infer_self_attn_with_kvcache(self, phase, grid_sizes, x, seq_lens, freqs, sh
rope_global_end = None if use_local_cache_rope else current_end
rope_sink_tokens = 0 if use_local_cache_rope else sink_tokens
q = self._apply_rope_with_cache_range(
phase,
q,
freqs,
h,
Expand All @@ -446,6 +448,7 @@ def infer_self_attn_with_kvcache(self, phase, grid_sizes, x, seq_lens, freqs, sh
sink_tokens=rope_sink_tokens,
)
attn_k = self._apply_rope_with_cache_range(
phase,
attn_k,
freqs,
h,
Expand Down
Loading