Kaixi 6c05aaae7e [trtllm_mha] perf: Stop allocating per-layer scratch inside the decode CUDA graph (#33063)

2026-08-04 19:27:26 -07:00

..

sglang

[trtllm_mha] perf: Stop allocating per-layer scratch inside the decode CUDA graph (#33063)

2026-08-04 19:27:26 -07:00

tools

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

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

MANIFEST.in

[Kernel] Move sgl-kernel under sglang.kernels.aot (#32648)

2026-07-29 17:25:00 +08:00

pyproject_cpu.toml

[core/loader] Add presharded load format (#24256)

2026-07-25 13:03:39 -07:00

pyproject_npu.toml

[core/loader] Add presharded load format (#24256)

2026-07-25 13:03:39 -07:00

pyproject_other.toml

Bump helion version to 1.4 (#32562)

2026-08-03 19:10:31 -07:00

pyproject_xpu.toml

[core/loader] Add presharded load format (#24256)

2026-07-25 13:03:39 -07:00

pyproject.toml

[Kimi] Support kimi-k3 (#32541)

2026-08-04 13:22:49 -07:00

setup.py

[mm] sglang-mm: server vision pipeline core (fetch/driver/pipeline) + Qwen VL (#32364)

2026-08-04 00:47:00 -07:00