vLLM/tests/v1/kv_connector/unit at 1806d1adfc9b598bc6eb94de38a330aaad04c291 - vLLM

offloading_connector

[kv_offload]: Add DSv4 support (#43142 )

2026-05-24 11:10:12 +03:00

__init__.py

[P/D] NIXL Integration (#17751 )

2025-05-12 09:46:16 -07:00

test_bidirectional_kv_transfer.py

[P/D] Prefill compute optimizations with bi-directional KV cache transfers between P and D nodes (#32553 )

2026-04-30 10:14:20 +00:00

test_cache_pollution_prevention.py

[P/D] KV Load Failure Recovery/Abort Configuration (#26813 )

2025-12-10 11:00:52 -08:00

test_config.py

[Feature] Support manually enabling the cumem allocator (#33648 )

2026-05-20 08:58:30 -04:00

test_decode_bench_connector.py

[Spec Decode] Support hybrid attention models in extract_hidden_states (#39949 )

2026-05-13 10:45:53 -07:00

test_error_propagation.py

[Perf] Optimize scheduler overhead for PD disaggregation, around 5% E2E perf improvement (#35781 )

2026-03-10 21:25:30 -07:00

test_example_connector.py

[Mypy] Better fixes for the mypy issues in vllm/config (#37902 )

2026-03-25 06:14:43 -07:00

test_flexkv_connector.py

[KV Connector] Support using FlexKV as KV Cache Offloading option. (#34328 )

2026-03-12 00:46:20 -07:00

test_hf3fs_client.py

[KVConnector] Support 3FS KVConnector (#37636 )

2026-04-07 15:46:00 +00:00

test_hf3fs_connector.py

[KVConnector] Support 3FS KVConnector (#37636 )

2026-04-07 15:46:00 +00:00

test_hf3fs_metadata_server.py

[KVConnector] Support 3FS KVConnector (#37636 )

2026-04-07 15:46:00 +00:00

test_invalid_blocks_correctness.py

[Perf] Optimize scheduler overhead for PD disaggregation, around 5% E2E perf improvement (#35781 )

2026-03-10 21:25:30 -07:00

test_kv_cache_layout.py

[Bugfix] Disable cross-layer KV cache for MLA attention backends (#37090 )

2026-03-16 19:03:10 +02:00

test_kv_connector_lifecycle.py

[Spec Decode] Support hybrid attention models in extract_hidden_states (#39949 )

2026-05-13 10:45:53 -07:00

test_kv_load_failure_recovery.py

[Perf] Optimize scheduler overhead for PD disaggregation, around 5% E2E perf improvement (#35781 )

2026-03-10 21:25:30 -07:00

test_lmcache_connector.py

[Prefix Cache] Include lora_name in BlockStored event for deterministic KV-cache reconstruction (#27577 )

2025-12-30 00:17:16 +00:00

test_lmcache_integration.py

[V0 Deprecation] Deprecate virtual engine (#37195 )

2026-03-18 14:30:14 -07:00

test_mooncake_connector_hma.py

[KV Connector] Remove compat support for pre-v0.12.0 constructor signatures without KVCacheConfig (#39832 )

2026-05-09 23:39:46 +00:00

test_mooncake_connector.py

[KV Connector] Remove compat support for pre-v0.12.0 constructor signatures without KVCacheConfig (#39832 )

2026-05-09 23:39:46 +00:00

test_mooncake_stats.py

[P/D][Mooncake] Add KVConnectorStats for transfer observability (#40414 )

2026-05-05 02:17:38 -07:00

test_mooncake_store_connector.py

[Mooncake] Add metrics for MooncakeStoreConnector operations (#43392 )

2026-05-23 13:34:40 -07:00

test_mooncake_store_coordinator.py

[KVConnector][DSV4] HMA support for Mooncake store connector (#42828 )

2026-05-19 01:07:46 -07:00

test_mooncake_store_hma_e2e.py

[KVConnector][DSV4] HMA support for Mooncake store connector (#42828 )

2026-05-19 01:07:46 -07:00

test_mooncake_store_scheduler.py

[KV Connector] Keep MooncakeStore full hits block-aligned (#43494 )

2026-05-23 23:15:03 -07:00

test_mooncake_store_worker.py

[Mooncake] Add metrics for MooncakeStoreConnector operations (#43392 )

2026-05-23 13:34:40 -07:00

test_moriio_connector.py

[KV Connector] Remove compat support for pre-v0.12.0 constructor signatures without KVCacheConfig (#39832 )

2026-05-09 23:39:46 +00:00

test_multi_connector.py

Keep scheduler alive for delayed KV connector frees (#43433 )

2026-05-23 06:23:32 +00:00

test_nixl_connector_hma.py

[Bugfix] mamba: run single-token extends as decodes (#42430 )

2026-05-18 15:26:00 +00:00

test_nixl_connector.py

[KV Connector][NIXL][Bugfix] Fix NIXL handshake failures not honoring kv_load_failure_policy (#40364 )

2026-05-11 09:37:21 +00:00

test_nixl_heartbeat.py

[Nixl][PD] Lease renewal TTL KV blocks on P (#41383 )

2026-05-11 09:27:30 +00:00

test_offloading_connector.py

[kv_offload] Add multi-tier KV cache offloading framework (#40020 )

2026-05-13 17:21:43 +03:00

test_output_aggregator.py

[Core] Simplify async KV output aggregation (#28327 )

2025-11-09 09:44:13 -08:00

test_remote_decode_lifecycle.py

[Core][KVConnector] Support HMA+NixlConnector (#35758 )

2026-03-06 08:51:21 +01:00

test_remote_prefill_lifecycle.py

[KVConnector][NIXL] Organize NIXL connector into its own directory (#39354 )

2026-04-12 13:10:50 +00:00

test_rixl_gpu_mem_diag.py

[ROCm][Engine] Fix GPU memory leaks in engine shutdown and test workaround for async KV prefix cache reset (#38503 )

2026-04-25 05:25:20 +00:00

test_scheduler_kv_connector_override.py

[KV Connector] Remove compat support for pre-v0.12.0 constructor signatures without KVCacheConfig (#39832 )

2026-05-09 23:39:46 +00:00

test_tp_mapping.py

[Bugfix][PD] Fix DSv4 Disaggregated (#41957 )

2026-05-09 16:48:24 +00:00

utils.py

[Spec Decode] Support hybrid attention models in extract_hidden_states (#39949 )

2026-05-13 10:45:53 -07:00