Longzhi Wang daaf498213 [Feature] support compute shared experts before combine for better overlap (#6697) ...

* [Feature] support compute shared experts before combine for better overlap

* fix test

* fix xpu

* fix

2026-03-17 15:18:51 +08:00

..

allreduce_deterministic.py

[Feature] Add Deterministic Inference Support (#6476)

2026-02-26 19:31:51 -08:00

chunked_moe.py

[Feature] support compute shared experts before combine for better overlap (#6697)

2026-03-17 15:18:51 +08:00

custom_all_reduce.py

[BugFix]Dev fix custom ar unstable result (#4437)

2025-10-17 11:47:16 +08:00

test_allreduce_deterministic_launch.py

[Feature] Add Deterministic Inference Support (#6476)

2026-02-26 19:31:51 -08:00

test_chunked_moe.py

[CI] Allow occasional distributed worker exit_code (#5341)

2025-12-03 10:56:59 +08:00

test_communication_fallback.py

[BugFix][Optimization] Replace silent failures with catchable exceptions and informative error messages (#6533)

2026-03-16 21:32:43 +08:00

test_communication.py

[Feature][OP] Add batch-invariant RMSNorm kernel and TP embedding Custom AR path (#6749)

2026-03-13 14:34:44 +08:00

test_cuda_wrapper.py

[CI] Add five unittest (#4958)

2025-11-12 10:43:33 +08:00

test_custom_all_reduce.py

[CI] Allow occasional distributed worker exit_code (#5341)

2025-12-03 10:56:59 +08:00

test_custom_allreduce_guard.py

[BugFix][Optimization] Replace silent failures with catchable exceptions and informative error messages (#6533)

2026-03-16 21:32:43 +08:00

test_fusedmoe_ep_entry.py

seq_lens related tensor shape -> [max_num_seqs] (#6535)

2026-03-02 11:18:30 +08:00

test_fusedmoe_tp_entry.py

initial commit (#6054)

2026-01-16 10:49:38 +08:00