FA3 speed up: skip len operation and get batch size directly from forward batch (sgl-project#5969)

Signed-off-by: Lifu Huang <[email protected]>

Author: lifuhuang

python/sglang/srt/layers/attention/flashattention_backend.py

@@ -342,7 +342,7 @@ def init_forward_metadata(self, forward_batch: ForwardBatch):
         """Initialize forward metadata hence all layers in the forward pass can reuse it."""
         metadata = FlashAttentionMetadata()
         seqlens_in_batch = forward_batch.seq_lens
-        batch_size = len(seqlens_in_batch)
+        batch_size = forward_batch.batch_size
         device = seqlens_in_batch.device
 
         if forward_batch.forward_mode.is_decode_or_idle():