Frank e2085f1f7d frank-default-small: use split-mode none on single-GPU dankserver ...

--split-mode graph requires >= 2 devices in ik_llama.cpp and errors hard
at model load on a single RTX 3090 ("It is not possible to use split mode
'graph' with less than 2 devices"), looping the service. Set SPLIT_MODE
=none (the default), which works with the --override-tensor CPU expert
offload. KB updated with the two-device requirement so we do not assume
graph degrades gracefully on one GPU.

2026-08-26 03:06:30 -07:00

..

.obsidian

Clarify llama-bench harness scope

2026-08-25 19:07:46 -07:00

Architecture

Document canonical Caddy migration

2026-08-25 21:59:59 -07:00

Dankclaw

Document canonical Caddy migration

2026-08-25 21:59:59 -07:00

Dankserver

Add CLI helper for entropy volume

2026-08-25 15:38:57 -07:00

Infrastructure

fix: use tls_insecure_skip_verify token (this Caddy build has no tls{} transport sub-block)

2026-08-26 02:16:42 -07:00

LLM

frank-default-small: use split-mode none on single-GPU dankserver

2026-08-26 03:06:30 -07:00

Research

docs(kv): add bit-density KV cache quant table across 3 runtimes

2026-08-25 20:03:13 -07:00

index.md

frank-default-small: use split-mode none on single-GPU dankserver

2026-08-26 03:06:30 -07:00

log.md

fix: proxy Plex through a TLS upstream (PMS drops plain HTTP off-loopback)

2026-08-26 01:27:33 -07:00