leavelet 9dd83bcb88 CP HiCache metrics: cover pure-L2 (no L3), lazily create the collector when L2 pooling is on ...

The collector was created only in _maybe_init_cp_l3 (enable_cp_l3 path), so a pure-L2-pooling
deployment (no L3) got no L2 metrics -- exactly the config under perf investigation. Move creation
into _cp_maybe_collect_metrics: lazily create on first emit, gated on enable_metrics + the shared-L2
allocator existing (L2 pooling on). collect() already handles l3_stats=None, so it reports L2
occupancy/commit/evict with or without L3.

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

2026-06-23 09:37:11 +00:00

..

sglang

CP HiCache metrics: cover pure-L2 (no L3), lazily create the collector when L2 pooling is on

2026-06-23 09:37:11 +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

new pyprojectoml

2026-06-10 05:54:43 +08:00