docs(char-rp-gguf): record custom llama.cpp build (master 6eddde0 + unmerged PR #25544)

Browse Source

Durable record of the custom llama.cpp the char-rp-reasoning seat will run to
fix Worldtree #355 (reasoning-budget forcing broken in stock b8840 — single
end-tag </think> can't match Qwen3.5's <tool_call> reasoning terminator, so the
budget never force-closes and reasoning runs away to max_tokens). PR #25544
adds multiple terminating sequences; unmerged upstream, so we build it.

- build.sh: reproducible recipe (clone master@6eddde0 + merge PR #25544 +
  resolve the 1 server-common.cpp conflict + CUDA build for Blackwell sm_120)
- README.md: why + acceptance test + rollback + REMOVE-WHEN-MERGED tracking

Image llamacpp-charrp:6eddde0-pr25544 BUILT + smoke-tested on ana-ml2; seat
swap pending. See also auto-memory reference_charrp_custom_llamacpp_pr25544.

...

This commit is contained in:

vh

2026-07-13 13:37:00 -07:00

parent 26b30d8231

commit 6cf3e78973

3 changed files with 192 additions and 14 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

persistent-memory.md

+18 -14

File diff suppressed because one or more lines are too long