aoshen02 039ea82660 [Core] Sync DP state on the first step of a wave (#52957) ...

Signed-off-by: aoshen02 <aoshen@inferact.ai>

2026-09-06 02:16:58 +00:00

..

__init__.py

[V1] AsyncLLM Implementation (#9826)

2024-11-11 23:05:38 +00:00

conftest.py

[Misc] Remove isort and yapf ignores (#26888)

2025-10-15 12:09:03 +00:00

test_abort_final_step.py

[MRV2] Also enable MRV2 for Llama and Mistral dense models (#43458)

2026-06-02 11:18:46 -07:00

test_admission_control.py

[Core] Add max_num_queued_reqs and max_num_queued_tokens for queue size management (#49445)

2026-08-31 14:26:49 +00:00

test_async_llm.py

[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

2026-07-29 04:20:40 +00:00

test_core_engine_actor_manager.py

[Frontend] Watch frontend processes during engine startup (#43417)

2026-08-06 11:17:24 -07:00

test_dp_placement_node_allowlist.py

[Core][Engine] allow DP ray placement groups to be set on specific nodes (#44669)

2026-06-05 20:07:47 +00:00

test_engine_args.py

Promote prefix_cache_retention_interval to an argument and change the default to 0 (#52216)

2026-08-17 13:20:50 +00:00

test_engine_core_client.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

test_engine_core.py

[Core] Sync DP state on the first step of a wave (#52957)

2026-09-06 02:16:58 +00:00

test_fast_incdec_prefix_err.py

[Refactor] Simplify BOS/EOS token handling (#34435)

2026-02-12 18:18:24 -08:00

test_init_error_messaging.py

[Bugfix][Core] Reserve the KV null block when validating max_model_len (#47272)

2026-08-20 02:49:23 +00:00

test_input_processor_trace_replay.py

[Core][V1] Support trace_decode_token_ids for deterministic decode replay (#46701)

2026-08-20 15:12:43 +08:00

test_iteration_logging.py

[Refactor] Move iteration logging to the frontend (#46647)

2026-07-15 17:59:05 -07:00

test_llm_engine_finalizer_is_weak.py

[Bugfix][MRV2] Release model and KV cache on in-process engine shutdown (#54162)

2026-08-28 22:09:08 -07:00

test_llm_engine.py

[UT][XPU] fix test_parallel_sampling due to global random state (#42388)

2026-05-12 18:03:23 +08:00

test_logprobs_processor.py

[Model Runner V2] Bug fix: logprob dtype int64/int32 issue (#41761)

2026-05-11 21:55:43 +00:00

test_output_processor.py

[Bugfix] Handle empty FlatLogprobs slices and delta output (#53704)

2026-08-26 21:00:54 +08:00

test_parallel_sampling.py

feat(frontend): session id plumbing into requests (#48048)

2026-08-03 22:18:58 +00:00

test_preprocess_error_handling.py

[XPU][CI]skip test_preprocess_error_handling due to fork/spawn issue (#31381)

2025-12-26 21:40:44 +00:00

test_startup_watch_processes.py

[ROCm] Give EngineCore cleanup grace after request abort (#52281)

2026-08-19 11:39:59 -05:00

utils.py

[Bugfix][Test] Fix off-by-one error in sampled token rank causing flaky logprobs test (#53976)

2026-08-31 18:49:43 +00:00