leavelet 76dc60a1d0 test(disagg): finish() latency breakdown instrumentation (lever A A5 root-cause) ...

Log per-request finish breakdown (wait_workers / fallback / wait_rdma) to prove
WHY the per-layer transfer stage (~193ms) doesn't shrink vs the monolithic (~172ms)
— i.e. whether the workers fall behind the forward (submits land late, no overlap)
or the RDMA itself is the cost. INFO-gated.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-07 09:51:05 +00:00

..

sglang

test(disagg): finish() latency breakdown instrumentation (lever A A5 root-cause)

2026-06-07 09:51:05 +00:00

pyproject_cpu.toml

Upgrade transformers==5.3.0 (#17784)

2026-03-18 13:50:43 -07:00

pyproject_npu.toml

Upgrade transformers==5.3.0 (#17784)

2026-03-18 13:50:43 -07:00

pyproject_other.toml

chore: extract diffusion_common in python/pyproject_other.toml (#20803)

2026-03-19 10:39:16 +08:00

pyproject_xpu.toml

Upgrade transformers==5.3.0 (#17784)

2026-03-18 13:50:43 -07:00

pyproject.toml

Upgrade transformers==5.3.0 (#17784)

2026-03-18 13:50:43 -07:00