[Bugfix] GLM-5.3-Flash: launch the kpool paged MQA logits in the varlen mode its schedule was built with (#55270)

Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
Yifan Qiao
2026-09-25 00:13:55 +00:00
committed by GitHub
co-authored by Claude Fable 5.1
parent 064bc747ab
commit 39724758e7
@@ -558,6 +558,7 @@ def sparse_attn_indexer_kpool(
decode_metadata.schedule_metadata,
max_model_len=max_pool_len,
clean_logits=False,
indices=decode_metadata.indices,
)
num_rows = logits.shape[0]
# kpool: logits are pool-granular -> select topk_tokens//kpool pools,