Yujun Dong 8ba9646044 Make GDN support non-continuous B/A Tensor input to fix the accuracy regression of Qwen3.5-27B (#22312) ...

Signed-off-by: cs-cat <118669451+cs-cat@users.noreply.github.com>

2026-04-10 18:58:13 +08:00

..

sglang

Make GDN support non-continuous B/A Tensor input to fix the accuracy regression of Qwen3.5-27B (#22312)

2026-04-10 18:58:13 +08:00

tools

Fix get_version_tag.py to handle dot-separated post versions (#22385)

2026-04-08 15:18:22 -07:00

pyproject_cpu.toml

[Fix] Fix setuptools-scm version resolution for rc tags (#22165)

2026-04-05 16:55:32 -07:00

pyproject_npu.toml

[Fix] Fix setuptools-scm version resolution for rc tags (#22165)

2026-04-05 16:55:32 -07:00

pyproject_other.toml

[Apple Silicon] [MLX] Add mlx and mlx-lm dependencies (#22162)

2026-04-07 11:36:43 +08:00

pyproject_xpu.toml

[Fix] Fix setuptools-scm version resolution for rc tags (#22165)

2026-04-05 16:55:32 -07:00

pyproject.toml

chore: bump flashinfer version to 0.6.7.post3 (#22382)

2026-04-08 14:49:45 -07:00