kyle/imladris
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
427 Commits 1 Branch 0 Tags
master
Commit Graph
5 Commits
Author SHA1 Message Date
kyle 623d68c38a ripgrep 2026-09-19 02:17:41 -07:00
kyle c5fed8c604 straylight: raise OpenCode and llama-server timeouts to 2h 
Local prefill and reasoning/coding turns often sit idle past OpenCode's
5–10 minute defaults. Align llama-server --timeout with that window.
 2026-09-17 05:49:52 -07:00
kyle 1e94e6638e straylight: local Whisper ASR and Qwen3.8-Flash-Next uncensored 
whisper.cpp large-v3-turbo on :11435 (CPU, OpenAI transcriptions path)
so ASR does not take GTT from llama-server. Flash-Next is the cygnal
IQ4_XS-NGQ4 GGUF (~98 GB, gfx1151), qwen4exp, mmproj pinned; unload
Laguna before loading.
 2026-09-16 07:18:28 -07:00
kyle 927eff0c98 straylight: treat Ornith 1.5 9B as a VLM 
Loaded instance reports image input; llama.cpp attaches mmproj-Q8_0
from the HF cache. Mark it vision in OpenCode and drop the old
text-only comment.
 2026-09-16 06:41:01 -07:00
kyle 52859524d7 straylight: install OpenCode config for local llama.cpp models 
Managed /etc/opencode/opencode.json points at straylight:11434 with
the router model ids, Laguna as default, Ornith 1.5 9B as small_model,
and a vision subagent on Qwen3-VL-8B abliterated.
 2026-09-16 06:34:41 -07:00