Trevor Morris 0eea17e3b5 Use dual stream for DS MoE whenever cuda graph is used (instead of with token threshold) (#9405)

2025-11-22 00:37:41 -08:00

..

sglang

Use dual stream for DS MoE whenever cuda graph is used (instead of with token threshold) (#9405)

2025-11-22 00:37:41 -08:00

pyproject_cpu.toml

chore: bump SGLang version to 0.5.5.post3 (#13366)

2025-11-16 17:55:38 -08:00

pyproject_other.toml

[NPU] chore: bump to CANN 8.3.RC1 and Pytorch 2.8.0 (#13647)

2025-11-21 17:07:08 +08:00

pyproject_xpu.toml

chore: bump SGLang version to 0.5.5.post3 (#13366)

2025-11-16 17:55:38 -08:00

pyproject.toml

chore: bump sgl-kernel version to 0.3.17.post2 (#13570)

2025-11-19 14:02:57 -08:00