arm=main tag=m1 ready_s=109 at=2026-09-13T21:44:20Z
NOTE: transcribed from the session; see boot_branch_b1.txt.
== 21:44:23 ==
source_digest: 5a66607a9ad0809e
server_info:   {'max_context': 186624, 'max_batch': 8}
kv metrics:
arbi_serve_kv_pool_pages_total{backend="paged_kv:tkv-k4v4",kind="paged_kv"} 730.0
arbi_serve_kv_pool_pages_total{backend="",kind="gdn"} 730.0
--- boot lines ---
21:44:15 WARNING max_context=auto: served context NARROWED to 183808 tokens (from the 262144-token sizing bound). This is the REAL served-context statement -- the KV pool is realized: 730 servable pages x 256 tokens/page, less the 11-page capture-sentinel prefix and a 0-page allocator margin.
21:44:15 INFO    Boot: KV cache ready at 3.03 GiB (13% of 23.52 GiB) -- 730 pages x 256 tok/page = 186880 servable tokens, free 0.39 GiB (2% of 23.52 GiB)
21:44:15 INFO    max_context=auto: widened served context to 186624 tokens to use the full realized KV pool (730 servable pages).
