[Generative Score API] Multi-Item scoring with custom attention mask. (#10979)

2025-10-08 18:47:32 -07:00
parent e22b13c569
commit 53bd00d975
10 changed files with 1121 additions and 129 deletions
--- a/python/sglang/srt/two_batch_overlap.py
+++ b/python/sglang/srt/two_batch_overlap.py
@@ -667,6 +667,7 @@ class TboForwardBatchPreparer:
            "can_run_dp_cuda_graph",
            "dp_padding_mode",
            "global_forward_mode",
+            "is_prefill_only",
            "spec_algorithm",
            "capture_hidden_mode",
            "padded_static_len",