..
ep_test_utils.py
[ep] Avoid mooncake ep test crash when ibgda_init fails ( #1410 )
2026-01-30 15:31:16 +08:00
test_batch_replica_clear.py
[Store] Expose batch_replica_clear in Python binding ( #1848 )
2026-04-17 17:36:32 +08:00
test_cli.py
[Store] feat: Add standalone deployment implementation for Client ( #1084 )
2025-11-25 23:57:30 +08:00
test_distributed_object_store.py
[store] Add get_into_ranges to support Grouped Scatter RDMA Reads ( #1717 )
2026-04-10 18:31:09 +08:00
test_distributed_object_store_cxl.py
[Store] feat: CXL storage full features. ( #1531 )
2026-02-24 19:59:45 +08:00
test_dummy_client.py
[store] Add get_into_ranges to support Grouped Scatter RDMA Reads ( #1717 )
2026-04-10 18:31:09 +08:00
test_import_structure.py
[Build] Deprecate stale adaptor usage to reduce whl package size ( #529 )
2025-06-20 14:19:41 +08:00
test_meta_server.py
[coro_rpc] use client pool and enable rdma ( #789 )
2025-09-02 00:40:21 +08:00
test_mooncake_backend.py
[PG] Add GPU barrier support for mooncake-pg ( #1751 )
2026-03-27 12:51:01 +08:00
test_mooncake_backend_chunk.py
Split Mooncake PG out of Mooncake EP ( #1387 )
2026-01-16 13:39:37 +08:00
test_mooncake_backend_cpu.py
[PG] Impelemented support for additional collective primitives: **`gather`**, **`scatter`**, and **`reduce`** in the Mooncake backend ( #1469 )
2026-02-01 17:46:02 +08:00
test_mooncake_backend_elastic.py
[PG][TE][TENT] Add dedicated peer liveness probe for recovery and enable elastic GPU test ( #1808 )
2026-04-08 09:56:58 +08:00
test_mooncake_backend_p2p_cpu.py
Split Mooncake PG out of Mooncake EP ( #1387 )
2026-01-16 13:39:37 +08:00
test_mooncake_backend_perf.py
Split Mooncake PG out of Mooncake EP ( #1387 )
2026-01-16 13:39:37 +08:00
test_mooncake_config.py
[Store] feat: support load config from env for mooncake store_service ( #951 )
2025-10-23 14:47:40 +08:00
test_mooncake_ep.py
[EP] In-place Member Update ( #1630 )
2026-03-09 11:32:06 +08:00
test_multi_dummy_clients.py
feat(Store): Support Connecting Multiple Dummy Clients to One Real Client ( #1122 )
2025-11-28 17:59:09 +08:00
test_put_get_tensor.py
[Store] Enlarge the Default KV TTL to 5 Seconds ( #660 )
2025-07-24 10:34:35 +08:00
test_regmr_overhead.py
[performance] decrease regmr overhead in ep_buffer/gda path ( #1414 )
2026-01-22 01:18:30 +08:00
test_replicated_distributed_object_store.py
[Store] Fix `with_hard_pin` failure in python API ( #1873 )
2026-04-12 23:22:23 +08:00
test_safetensor_functions.py
[Store] add safe tensor API ( #1199 )
2026-02-26 10:11:10 +08:00
test_ssd_offload_in_evict.py
[Store]feat: Migrate Persistence Metadata from Client to Master Service ( #690 )
2025-08-14 14:34:51 +08:00
test_transfer_on_cuda.py
[TE] Support transfer in cuda stream via cudaLaunchHostFunc ( #1448 )
2026-01-28 17:15:20 +08:00
test_transfer_on_hip.py
[TransferEngine][ROCm] Add ROCm HIP support to the Mooncake Python package ( #1742 )
2026-04-13 11:13:10 +08:00
transfer_engine_initiator_test.py
[Wheel] Remove the default buffer pre-allocation in initialize() ( #1415 )
2026-01-21 23:14:41 +08:00
transfer_engine_target.py
[Wheel] Remove the default buffer pre-allocation in initialize() ( #1415 )
2026-01-21 23:14:41 +08:00
28464f3aee