Jialin Ouyang 186352b270

[Core] Performance: Use list[np.ndarray] instead of list[list[int]] for output tokens for GC optimization (#26368) ...

Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>

2025-11-14 16:04:04 -08:00

..

__init__.py

…

test_async_scheduler.py

[Core] Performance: Use list[np.ndarray] instead of list[list[int]] for output tokens for GC optimization (#26368)

2025-11-14 16:04:04 -08:00

test_encoder_cache_manager.py

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

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

test_kv_cache_utils.py

[Bugfix] TypeError: 'NoneType' object is not callable (#27410)

2025-11-14 21:13:53 +00:00

test_kv_sharing.py

[V0 Deprecation] Remove VLLM_USE_V1 from tests (#26341)

2025-10-07 15:42:31 +00:00

test_prefix_caching.py

[BugFix][LoRA] use adapter_id instead of id field of lora_request (#27728)

2025-11-03 10:08:08 +08:00

test_priority_scheduler_random.py

[BugFix] Priority scheduling and spec tokens preemption (#28558)

2025-11-12 20:29:21 +00:00

test_scheduler_e2e.py

[CI] Replace large models with tiny alternatives in tests (#24057)

2025-10-16 15:51:27 +01:00

test_scheduler.py

[Core] Performance: Use list[np.ndarray] instead of list[list[int]] for output tokens for GC optimization (#26368)

2025-11-14 16:04:04 -08:00

test_single_type_kv_cache_manager.py

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

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

utils.py

[KV Connector] Test async mode in scheduler tests (#28550)

2025-11-13 18:30:59 -05:00