omerpaz95 7227d06156 [Metrics] [KVConnector] Add Offloading Connector metrics (#27942) ...

Added queries and hits metrics for the Offloading Connector.

Also added timing metrics for store and load operations, which take the
average time it takes to load/store, per-token.

The metrics are available from Prometheus and from the StatLogger.

Signed-off-by: omerpaz95 <omerpaz95@gmail.com>
Co-authored-by: Omer Paz <Omer.Paz@ibm.com>

2026-01-27 13:34:49 +00:00

..

__init__.py

[P/D] NIXL Integration (#17751)

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

test_backwards_compatibility.py

[1/N][Attention] Restructure attention: move files (#31916)

2026-01-09 13:10:24 -08:00

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

[UX] Use kv_offloading_backend=native by default (#32421)

2026-01-15 18:55:11 +00:00

test_decode_bench_connector.py

[Performance] Split FlashAttn attention and cache update (#25954)

2026-01-23 17:28:06 -08:00

test_error_propagation.py

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

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

test_example_connector.py

[Chore] Remove unused noqas (#31263)

2025-12-24 05:38:46 -08:00

test_invalid_blocks_correctness.py

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

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

test_kv_connector_lifecyle.py

kv_transfer: Rename the shared storage connectors (#30201)

2025-12-08 20:46:09 -08:00

test_kv_load_failure_recovery.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -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

[CI]: Remove unnecessary imports from test_lmache_integration (#30157)

2025-12-06 12:53:34 +08:00

test_moriio_connector.py

[ROCm][PD] add moriio kv connector. (#29304)

2026-01-09 14:01:57 +00:00

test_multi_connector.py

[KVConnector]: Enable Cross-layers KV cache layout for MultiConnector (#30761)

2026-01-07 16:59:43 +00:00

test_nixl_connector.py

[Performance] Split FlashAttn attention and cache update (#25954)

2026-01-23 17:28:06 -08:00

test_offloading_connector.py

[Metrics] [KVConnector] Add Offloading Connector metrics (#27942)

2026-01-27 13:34:49 +00:00

test_output_aggregator.py

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

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

test_remote_decode_lifecycle.py

[NIXL] Ignore abort on already-finished request (#25067)

2025-10-10 12:21:56 +02:00

test_remote_prefill_lifecycle.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

utils.py

Decouple page_size_bytes calculation in AttentionSpec for TPU/RPA Compatibility. (#31635)

2026-01-08 09:00:07 +00:00