Yuxuan ZhangandXinyuan Tong 9f21fbc34b [GLM-5.3-Flash] Reduce KPool planning synchronization and overlap indexer preparation (#39695) ...

Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>

2026-09-19 23:51:17 -07:00

..

test_decode_cuda_graph_runner.py

chore: update CI test est_time values (#38238)

2026-09-06 17:49:41 -07:00

test_decode_cuda_graph_shared_read_fence.py

chore: update CI test est_time values (#38238)

2026-09-06 17:49:41 -07:00

test_flashinfer_autotune_sync.py

dsv4.1: remaining model and runtime integration (#38798)

2026-09-18 02:55:30 -07:00

test_hidden_state_graph_recapture.py

[DSV4][BCG] Optimize the heavy memory use of C4 Indexer when BCG is enabled (#36534)

2026-09-15 17:23:11 -07:00

test_prefill_cuda_graph_padding.py

[GLM-5.3-Flash] Reduce KPool planning synchronization and overlap indexer preparation (#39695)

2026-09-19 23:51:17 -07:00

test_prefill_shared_read_done.py

[Spec] Add explicit prefill shared-read capability for plugins (#39502)

2026-09-18 13:11:01 -07:00