Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Fix hidream o1 regression. (#14923)

comfyanonymousc35a622acdab
diff --git a/comfy/ldm/hidream_o1/attention.py b/comfy/ldm/hidream_o1/attention.py
index 1b68f1771..afb2be9b8 100644
--- a/comfy/ldm/hidream_o1/attention.py
+++ b/comfy/ldm/hidream_o1/attention.py
@@ -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)