vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

feat(char-rp-gguf): swap reasoning seat to custom llama.cpp (master 6eddde0 + PR #25544)

Browse Source 
The char-rp-reasoning (Deckard) seat now runs llamacpp-charrp:custom-latest via a
new LLAMA_REASONING_IMAGE var (Magidonia char-rp stays on stock — no reasoning bug).
Fixes Worldtree #355 at the source (budget multi-terminator handles Qwen3.5's
<tool_call> reasoning end-tag). Live 2026-07-13: Deckard loads on Blackwell, serves
coherent, reasoning bounds at the 400 budget. Rollback via .env LLAMA_REASONING_IMAGE.
This commit is contained in:
vh
2026-07-13 13:47:42 -07:00
parent 6cf3e78973
commit 85792f4b55
3 changed files with 13 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
stacks/char-rp-gguf/compose.yaml
+7 -1
View File
@@ -96,7 +96,13 @@ services:
# ── REASONING seat — Deckard-PKD (Qwen3.5) managed thinking + DRY. gateway char-rp-reasoning. ──
llama-charrp-reasoning:
image: ${LLAMA_IMAGE:-ghcr.io/mostlygeek/llama-swap:cuda}
# ⚠️ CUSTOM llama.cpp build (master 6eddde0 + unmerged PR #25544) — the Worldtree
# #355 reasoning-budget-forcing fix (multi-terminator: handles Qwen3.5's <tool_call>
# reasoning end-tag, which stock b8840's single-</think> budget can't match → the seat
# loops in reasoning to max_tokens ≈ 22 min). DO NOT revert to a stock image until
# #25544 merges upstream. Build recipe + why + rollback: ./llamacpp-custom/README.md.
# Rollback: set LLAMA_REASONING_IMAGE=ghcr.io/mostlygeek/llama-swap:cuda in .env + recreate.
image: ${LLAMA_REASONING_IMAGE:-llamacpp-charrp:custom-latest}
container_name: ${CHARRP_REASONING_CONTAINER:-llama-charrp-reasoning}
restart: unless-stopped
runtime: nvidia