Cheng WanandClaude Opus 4.7 ad4994dc1d DeepseekV2MoE: defer shared experts when routed kernel is non-mutating (#25279) ...

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-14 22:20:55 -07:00

..

sglang

DeepseekV2MoE: defer shared experts when routed kernel is non-mutating (#25279)

2026-05-14 22:20:55 -07:00

tools

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

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

pyproject_cpu.toml

feat: use structural tags to enable strict tool calling and reasoning for more models (#21722)

2026-05-04 02:30:28 -07:00

pyproject_npu.toml

feat: use structural tags to enable strict tool calling and reasoning for more models (#21722)

2026-05-04 02:30:28 -07:00

pyproject_other.toml

[MUSA]: Add flashinfer sampling backend (#24978)

2026-05-14 20:23:15 -07:00

pyproject_xpu.toml

feat: use structural tags to enable strict tool calling and reasoning for more models (#21722)

2026-05-04 02:30:28 -07:00

pyproject.toml

revert flashinfer 0.6.11 bumps (#25310)

2026-05-14 15:28:58 -07:00