Xiaoyu ZhangandClaude Opus 4.8 a2d7eb303e [MoE] Consolidate ungrouped + grouped gate/topk onto one Triton router (#26771) — faster than AOT on B200/H100/H200, at parity with flashinfer (#29771) ...

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

2026-07-03 11:18:59 +08:00

..

sglang

[MoE] Consolidate ungrouped + grouped gate/topk onto one Triton router (#26771) — faster than AOT on B200/H100/H200, at parity with flashinfer (#29771)

2026-07-03 11:18:59 +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

[CPU] Fix model failures on Xeon (#29497)

2026-07-02 13:20:18 +08:00

pyproject_npu.toml

[Deps] Bump transformers to 5.12.1 (#29393)

2026-06-30 00:54:01 -07:00

pyproject_other.toml

[Deps] Bump transformers to 5.12.1 (#29393)

2026-06-30 00:54:01 -07:00

pyproject_xpu.toml

[Deps] Bump transformers to 5.12.1 (#29393)

2026-06-30 00:54:01 -07:00

pyproject.toml

Upgrading tvm-ffi/sgl-deep-gemm/tilelang (#29554)

2026-07-01 12:32:18 -07:00