Isotr0pyandGitHub 1173804dca [Bugfix] Fix TP inference for Flex attention backend (#19657) ...

Signed-off-by: Isotr0py <2037008807@qq.com>

2025-06-16 11:21:37 +00:00

..

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

conftest.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_async_llm.py

[Bugfix] Fix auto dtype casting for BatchFeature (#19316)

2025-06-14 15:13:08 +00:00

test_engine_args.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_engine_core_client.py

[Bugfix] Fix auto dtype casting for BatchFeature (#19316)

2025-06-14 15:13:08 +00:00

test_engine_core.py

[Bugfix] Fix TP inference for Flex attention backend (#19657)

2025-06-16 11:21:37 +00:00

test_fast_incdec_prefix_err.py

[BugFix] Work-around incremental detokenization edge case error (#19449)

2025-06-12 06:43:20 +00:00

test_llm_engine.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_output_processor.py

Allow AsyncLLMEngine.generate to target a specific DP rank (#19102)

2025-06-04 08:26:47 -07:00

utils.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00