Cyrus LeungandGitHub 66d433b94f [V1] Revert the default max_num_seqs to V0 values for most hardware (#16158) ...

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

2025-04-07 13:54:36 -04:00

..

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

conftest.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

test_async_llm.py

[V1] Minor V1 async engine test refactor (#15075)

2025-03-19 10:37:17 -07:00

test_engine_args.py

[V1] Revert the default max_num_seqs to V0 values for most hardware (#16158)

2025-04-07 13:54:36 -04:00

test_engine_core_client.py

[V1] AsyncLLM data parallel (#13923)

2025-03-27 16:14:41 -07:00

test_engine_core.py

[V1] Refactor num_computed_tokens logic (#15307)

2025-03-27 04:54:36 +00:00

test_llm_engine.py

[Core] Update dtype detection and defaults (#14858)

2025-03-19 13:49:33 +08:00

test_output_processor.py

[V1][Perf] Simpler request output queues (#15156)

2025-03-24 22:44:08 +00:00

utils.py

[V1] Detokenizer: Respect Stop Tokens + not include_stop_str_in_output (#14624)

2025-03-13 19:07:34 +00:00