Alison Shao 750ecf4a45 Add server CUDA graph warmup CI step for cold H200 nodes (#19201)

2026-02-24 16:07:01 -08:00

..

ci

Add server CUDA graph warmup CI step for cold H200 nodes (#19201)

2026-02-24 16:07:01 -08:00

ci_monitor

update pre-commit config (#18860)

2026-02-16 00:18:31 +08:00

code_sync

update pre-commit config (#18860)

2026-02-16 00:18:31 +08:00

playground

[Refactor] Benchmark: Add typed DatasetArgs/Loader registry and CPU dataset unit tests (#19147)

2026-02-24 12:22:01 -08:00

release

[NPU] Split pyproject npu from pyproject other (#17641)

2026-01-26 09:45:44 -08:00

check_vram_clear.sh

…

convert_otel_2_perfetto.py

[Feature] Sglang Tracing: Fine-Grained Tracking for Request Latency - Part 2 (#10804)

2025-10-28 01:25:46 -07:00

ensure_vram_clear.sh

…

export_deepseek_nextn.py

…

killall_sglang.sh

Pass GPU ids to kill specified devices in script. (#17840)

2026-01-27 13:52:55 -08:00

sort_testcases_alphabetically.py

Fix port conflicts in CI (#11497)

2025-10-12 06:46:36 -07:00

update_kernel_whl_index.py

[AMD] Add pip install / wheel build support for ROCm sgl-kernel (#15627)

2026-01-07 20:18:29 -08:00

update_nightly_whl_index.py

fix: move nightly whl to cuda version folder (#17762)

2026-01-27 00:13:46 +08:00

update_pr_whl_index.py

feature: PR wheel (#15170)

2025-12-15 00:22:47 -08:00

version_branch_to_tag.sh

…