vllm/model_executor at bde9e2272a28342d30fe9c4de4c1c9633ff153d8 - vllm - 丝路新云-代码仓

xinyun/vllm

mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-01 11:01:49 +08:00

History

Tao He bde9e2272a

[Bugfix][Qwen] fixes the weights dtype in qwen3_next: it is actually a bfloat16 (#27030 )

Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>

2025-10-17 03:37:52 +00:00

..

disable graph partition in custom op (#26952 )

2025-10-17 11:08:47 +08:00

[Chore] Separate out vllm.utils.importlib (#27022 )

2025-10-17 00:48:59 +00:00

[Bugfix][Qwen] fixes the weights dtype in qwen3_next: it is actually a bfloat16 (#27030 )

2025-10-17 03:37:52 +00:00

[Feature] Migrate DeepGEMM API from get_m_alignment_for_contiguous_layout to get_mk_alignment_for_contiguous_layout (#26935 )

2025-10-16 16:46:48 -04:00

__init__.py

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

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

custom_op.py

[FrontEnd] UNREVERT CompilationConfig overhaul (#20283 ): deprecate use_inductor in favor of backend, simplify custom_ops (#26502 )

2025-10-13 22:47:16 +00:00

parameter.py

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

2025-10-12 09:51:31 -07:00

utils.py

disable graph partition in custom op (#26952 )

2025-10-17 11:08:47 +08:00