Repository navigation
Commit 07b7c7e
Fix buffer dtype mismatch and causal mask recompute in export (pytorch#18380)
- Materialize state buffers as bf16 (not fp32) to match compute dtype,
fixing "Expected bfloat16 inputs" error in Triton SDPA during AOTI
lowering
- Use hasattr(layer.attn, "mask") instead of isinstance(layer.attn,
FullAttention) for causal mask recompute — the isinstance check fails
when the module is imported via different Python paths
(executorch.examples... vs examples...)
- Remove unused FullAttention import from export.py
- Fix model directory name in README examples (Qwen3.5-MoE-A3B →
Qwen3.5-35B-A3B)
Co-authored-by: mnachin <mnachin@fb.com>1 parent 1cbc24c commit 07b7c7e
2 files changed
Lines changed: 8 additions & 5 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
32 | 32 | | |
33 | 33 | | |
34 | 34 | | |
35 | | - | |
| 35 | + | |
36 | 36 | | |
37 | 37 | | |
38 | 38 | | |
| |||
73 | 73 | | |
74 | 74 | | |
75 | 75 | | |
76 | | - | |
| 76 | + | |
77 | 77 | | |
78 | 78 | | |
79 | 79 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
12 | 12 | | |
13 | 13 | | |
14 | 14 | | |
15 | | - | |
| 15 | + | |
16 | 16 | | |
17 | 17 | | |
18 | 18 | | |
| |||
129 | 129 | | |
130 | 130 | | |
131 | 131 | | |
| 132 | + | |
| 133 | + | |
132 | 134 | | |
133 | 135 | | |
| 136 | + | |
134 | 137 | | |
135 | 138 | | |
136 | 139 | | |
137 | 140 | | |
138 | | - | |
| 141 | + | |
139 | 142 | | |
140 | 143 | | |
141 | 144 | | |
| |||
153 | 156 | | |
154 | 157 | | |
155 | 158 | | |
156 | | - | |
| 159 | + | |
157 | 160 | | |
158 | 161 | | |
159 | 162 | | |
| |||
0 commit comments