Frank d317d6b246 frank-primary: 5th expert block onto ROCm0 (operator-directed fill) ...

Blocks 0-4 on ROCm0 + 45-47 on ROCm1. This exact shape was probed and
battery-verified earlier the same session: card0 2.54 GiB free at boot,
2.11 GiB after the vision graph (steady under load), card1 unchanged
at ~3.3 GiB. Card1 cannot take another block (0.82 GiB would OOM the
vision graph + boot drift), so 5/3 is the physical limit at the
4x262144 / V-q8_0 shape. OT assertion pins the new value.

2026-09-26 21:38:05 -07:00

..

.AGENTTRASH

feat(frank-medium): cut the endpoint over to radiance TP=2

2026-09-20 18:15:27 -07:00

patches

frank-default-large: re-enable --flash-attn on via QSA F32-mask patch

2026-08-29 23:43:25 -07:00

bench_tb_fixed.py

docs: rename docs/ -> serverAppConfigs-docs/ per system-wide PROJECTNAME-docs convention

2026-08-28 02:20:06 -07:00

bench-batch-ubatch.sh

scripts: fix the unbound local that killed the sweep at its first cell

2026-09-16 21:43:09 -07:00

bench-conversation.py

test(bench): drop the pre-probe from the conversation battery

2026-09-20 17:51:27 -07:00

bench-decode.sh

feat(llm): rename inference services dropping 'default' from names

2026-09-03 16:15:43 -07:00

bench-llm-soak.py

bench: commit the harnesses the frank-medium numbers came from

2026-09-16 06:59:44 -07:00

bench-threads-batch-http.py

feat(llm): rename inference services dropping 'default' from names

2026-09-03 16:15:43 -07:00

bench-threads-batch.sh

feat(llm): rename inference services dropping 'default' from names

2026-09-03 16:15:43 -07:00

bench-turn-latency.py

frank-medium: the agent-loop shape on one slot, and a harness header that matches the runtime

2026-09-16 15:38:20 -07:00

bench-ubatch.sh

feat(llm): rename inference services dropping 'default' from names

2026-09-03 16:15:43 -07:00

build-kairic-edge-gfx1151.sh

frank-large: swap to Kairic Edge 27B IU4 (W4A4) on Strix Halo

2026-09-21 18:56:35 -07:00

build-llama-rdna4.sh

build-llama-rdna4: bundle librocm-core

2026-09-20 15:25:09 -07:00

check-vault-links.py

docs: three dangling links, and a gate so they cannot accumulate

2026-09-16 07:43:33 -07:00

dankserver-route-primary.sh

add conversation-token battery and eno1 route preference

2026-09-20 15:25:09 -07:00

deploy-open-webui-quadlet.sh

Deploy services independently by changed paths

2026-08-25 20:13:33 -07:00

deploy-pihole-quadlet.sh

Deploy services independently by changed paths

2026-08-25 20:13:33 -07:00

deploy-plan.py

frank-primary: swap Dankserver to llama.cpp Qwen3.8-Flash-Next Q8_0

2026-09-26 19:45:28 -07:00

deploy-remote.sh

frank-primary: swap Dankserver to llama.cpp Qwen3.8-Flash-Next Q8_0

2026-09-26 19:45:28 -07:00

deploy-searxng-quadlet.sh

Deploy services independently by changed paths

2026-08-25 20:13:33 -07:00

deploy.sh

retire frank-medium: tests, planning and observability ground on frank-primary

2026-09-26 19:25:46 -07:00

download-frank-large-orca.sh

frank-small: revert vLLM cutover — back to llama.cpp Gemma4-12B Q4_K_M

2026-09-19 01:42:37 -07:00

download-frank-large-unsloth.sh

fix(frank-large): load the model as its native 3-way split, not a concatenated file

2026-09-21 13:58:54 -07:00

download-frank-large.sh

frank-large: swap to stock llama.cpp serving Qwen3.8-27B UD-Q8_K_XL with DFlash2

2026-09-21 21:50:36 -07:00

download-frank-primary.sh

add frank-primary payload fetch (Qwen3.8-Flash-Next Q8_0 + MTP head + mmproj)

2026-09-26 19:28:09 -07:00

dump-gguf.py

frank-primary: pin the -ot override set to the real tensor names

2026-09-26 19:51:57 -07:00

frank-large.env

frank-large: swap to stock llama.cpp serving Qwen3.8-27B UD-Q8_K_XL with DFlash2

2026-09-21 21:50:36 -07:00

frank-large.service

frank-large: swap to stock llama.cpp serving Qwen3.8-27B UD-Q8_K_XL with DFlash2

2026-09-21 21:50:36 -07:00

frank-primary.env

frank-primary: 5th expert block onto ROCm0 (operator-directed fill)

2026-09-26 21:38:05 -07:00

frank-primary.service

frank-primary: swap Dankserver to llama.cpp Qwen3.8-Flash-Next Q8_0

2026-09-26 19:45:28 -07:00

frank-small.env

perf(frank-small): cap the CPU RAM cache at 2048 MiB

2026-09-21 14:57:32 -07:00

frank-small.service

frank-small: revert vLLM cutover — back to llama.cpp Gemma4-12B Q4_K_M

2026-09-19 01:42:37 -07:00

generate-prompts.py

docs: rename docs/ -> serverAppConfigs-docs/ per system-wide PROJECTNAME-docs convention

2026-08-28 02:20:06 -07:00

hf-fetch.sh

hf-fetch: only pass -C - when a non-empty partial exists

2026-09-26 15:23:24 -07:00

hf-manifest.py

feat(frank-medium): swap MXFP4 -> FP8; add the one-command swap toolchain

2026-09-20 21:53:00 -07:00

homepage-status.py

homepage: sectioned panels, WIP open/closed, current model facts, Tautulli card

2026-09-21 13:20:15 -07:00

homepage-status.service

Homepage (TDD slice 6): the git-driven deploy

2026-08-23 12:59:56 -07:00

homepage-status.timer

Homepage (TDD slice 6): the git-driven deploy

2026-08-23 12:59:56 -07:00

mount-entropy.sh

Add CLI helper for entropy volume

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

qwen-sharp-v22.4.0.jinja

retire frank-medium: tests, planning and observability ground on frank-primary

2026-09-26 19:25:46 -07:00

serve-frank-large.sh

frank-primary + frank-large: export /metrics, raise primary log verbosity to 4

2026-09-26 20:58:53 -07:00

serve-frank-primary.sh

frank-primary: four full-window slots, V q8_0 KV, hot expert blocks on-GPU

2026-09-26 21:29:21 -07:00

serve-frank-small.sh

perf(frank-small): cap the CPU RAM cache at 2048 MiB

2026-09-21 14:57:32 -07:00

signal-relay.py

relay: restore SIGNAL_CLI constant dropped by a boundary-repaired edit

2026-09-17 18:38:54 -07:00

signal-relay.service

alerting: Alertmanager + Signal relay deliver firing rules to Frank's phone

2026-09-17 13:09:59 -07:00

test-changed.sh

frank-primary: swap Dankserver to llama.cpp Qwen3.8-Flash-Next Q8_0

2026-09-26 19:45:28 -07:00

tmux-resurrect.sh

feat: add tmux session snapshot and restore utility

2026-08-25 17:04:15 -07:00