anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[PERF] Wan2.2 support adalayernorm fused op (#2585)

Browse Source 
Signed-off-by: fan2956 <zhoufan53@huawei.com>
Co-authored-by: Canlin Guo <canlinguosdu@gmail.com>
This commit is contained in:
fan2956andCanlin Guo authored and GitHub committed 2026-04-15 14:02:41 +08:00
1 parent 1ad726f495
commit 2dff2d7c74
5 files changed
+45 -84
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

vllm_omni/diffusion/cache/teacache/extractors.py
Vendored
+2 -1
View File
@@ -222,7 +222,8 @@ def extract_qwen_context(
block = module.transformer_blocks[0]
img_mod_params = block.img_mod(temb)
img_mod1, _ = img_mod_params.chunk(2, dim=-1)
img_modulated, _ = block.img_norm1(hidden_states, img_mod1)
img_scale1, img_shift1, _ = block._modulate(img_mod1)
img_modulated = block.img_norm1(hidden_states, img_scale1, img_shift1)
# ============================================================================
# DEFINE TRANSFORMER EXECUTION (Qwen-specific)