Files
lerobot-clone/src/lerobot
Pepijn 3b4376aa33 fix(pi052): cast attention bias to model dtype for bf16 inference
`_prepare_attention_masks_4d` always returns fp32 (the 0.0 / -inf
literals); with bf16 weights, HF PaliGemma's SDPA path raises
"invalid dtype for bias - should match query's dtype" and
select_message returns empty every step. Cast in both attention
sites: `_compute_layer_ki` (training, when both experts run) and
`select_message` (inference, VLM-only branch). Bf16 training +
bf16 inference now run end to end with no dtype mismatch.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-20 18:42:26 +02:00
..