wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-07-18 12:28:17 +08:00
Code Issues Actions 30 Packages Projects Releases Wiki Activity

Fix hidream o1 regression. (#14923)

Browse Source
This commit is contained in:
comfyanonymous 2026-07-13 12:52:28 -07:00 committed by GitHub
parent da2608926e
commit c35a622acd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
comfy/ldm/hidream_o1/attention.py
View File

@ -15,24 +15,24 @@ def make_two_pass_attention(ar_len: int, transformer_options=None):
The AR pass goes through SDPA directand bypasses wrappers, it is only ~1% of T at typical edit sizes.
"""
def two_pass_attention(q, k, v, heads, **kwargs):
def two_pass_attention(q, k, v, heads, enable_gqa=False, **kwargs):
B, H, T, D = q.shape
if T < k.shape[2]: # KV-cache hot path: Q is shorter than K/V (cached AR prefix is in K/V only), all fresh Q positions are in the gen region, single full-attention call
out = optimized_attention(q, k, v, heads, mask=None, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options)
out = optimized_attention(q, k, v, heads, mask=None, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options, enable_gqa=enable_gqa)
elif ar_len >= T:
out = comfy.ops.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=0.0, is_causal=True)
out = comfy.ops.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=0.0, is_causal=True, enable_gqa=enable_gqa)
elif ar_len <= 0:
out = optimized_attention(q, k, v, heads, mask=None, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options)
out = optimized_attention(q, k, v, heads, mask=None, skip_reshape=True, skip_output_reshape=True, transformer_options=transformer_options, enable_gqa=enable_gqa)
else:
out_ar = comfy.ops.scaled_dot_product_attention(
q[:, :, :ar_len], k[:, :, :ar_len], v[:, :, :ar_len],
attn_mask=None, dropout_p=0.0, is_causal=True,
attn_mask=None, dropout_p=0.0, is_causal=True, enable_gqa=enable_gqa,
)
out_gen = optimized_attention(
q[:, :, ar_len:], k, v, heads,
mask=None, skip_reshape=True, skip_output_reshape=True,
transformer_options=transformer_options,
transformer_options=transformer_options, enable_gqa=enable_gqa,
)
out = torch.cat([out_ar, out_gen], dim=2)