Frank 2992a7ddd6 docs: record the wire rename, the OpenWebUI re-key, and the frank-primary bench drop-in trap ...

- AGENTS.md Model Config: the Protoss names are now the ids on the wire
  (per-endpoint knob named); verify a rename on /v1/models, never on a chat
  response — radiance echoes the requested name
- OMP Harness.md: harness id == served id; one id per model everywhere
- Homepage.md: the docs-page "api id" annotations and the switchover promise
  are retired
- OpenWebUI.md: the id-keyed trio (model row, access_grant, api_configs
  model_ids) is a foreign-key set — re-key it in the same deploy; plus the
  contenteditable-composer probe note
- frank-secondary/frank-large/frank-primary runbooks: served ids
  frank-zealot/frank-dragoon/frank-archon, and the bench.conf drop-in that
  made every frank-primary deploy since 2026-10-08 04:09 restart the staging
  worktree behind a green health gate

2026-10-09 17:06:44 -07:00

..

Pipeline Parallelism

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

agentionai-fast-imatrix.md

docs: rename frank-default-large/small/sightsound to frank-large/small/npu across vault

2026-09-03 16:17:14 -07:00

ciru-activefpx-promptforge.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

Dankclaw Improvements.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

Dankclaw System Specs.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

dankclaw-iommu-translation-off.md

feat(llm): swap frank-large to halogen-flash-server, retire frank-npu

2026-09-11 14:48:28 -07:00

Dankserver System Specs.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

dankserver-frontier-moe-feasibility.md

docs(fleet): radiance standalone engine probe - qwen4exp refuses fp8 input, quant happens at convert

2026-10-05 14:11:47 -07:00

dankserver-qwen38-fp8-expert-offload-tuning.md

docs(frank-primary): RESOLVED - the ~40k corruption was marginal DDR5 at 4800, fixed at 4600

2026-10-05 13:54:06 -07:00

dankserver-vram-growth.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

dealign-ornith-crack.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

deployment.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

dflash2-large-vulkan.md

docs: rename frank-default-large/small/sightsound to frank-large/small/npu across vault

2026-09-03 16:17:14 -07:00

DFlash DSpark Speculative Decoding.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

Dual-R9700-Cooperation.md

feat(monitoring,harness): follow frank-medium onto vllm:* metrics and fix red-by-construction targets

2026-09-20 19:35:56 -07:00

eemin-rocmi4-mtp.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

FastFlowLM NPU Inference.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-large-benchmark.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

frank-large-ciru-orca.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

frank-large-flash-server-v2-swift15.md

docs: record the wire rename, the OpenWebUI re-key, and the frank-primary bench drop-in trap

2026-10-09 17:06:44 -07:00

frank-large-gufo-qwen38-27b.md

docs: record the 2026-10-02 swaps — frank-large on ROCmFPX, frank-small on Q5_K_M

2026-10-02 01:51:11 -07:00

frank-large-halogen27b-dflash2.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-large-ik-uncensored.md

docs: distill the managed skill library into the vault (waves 1-7)

2026-10-05 21:19:15 -07:00

frank-large-kairic-edge-qwen38-27b.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

frank-large-rocmfpx-q6agent-uncensored-mtp.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-large-rocmfpx-q8agent-mtp.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-large-unsloth-qwen38-27b-q8xl.md

frank-large: replace stock llama.cpp with gufo (gufo-org/gufo) on Dankclaw

2026-09-28 22:08:29 -07:00

frank-large-unsloth-qwen38-flash-next.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

frank-large-vllm-mimo-v26-bf16.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-medium-batch-ubatch.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-medium-llamacpp-dflash2.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-medium-model-swap.md

test(frank-medium): A/B DFlash2 vs MTP on FP8 — DFlash2 wins on decode

2026-09-20 22:20:53 -07:00

frank-medium-radiance-mxfp4.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

frank-medium-rocmfpx.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-npu.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-primary-freetoken-pr587.md

frank-primary: radiance native-FP8 TP=2 cutover (engine, payload build, rollback)

2026-10-05 23:26:51 -07:00

frank-primary-glm53-flash-w4a16.md

docs: distill the managed skill library into the vault (waves 1-7)

2026-10-05 21:19:15 -07:00

frank-primary-llamacpp-qwen38-flash-next-q8.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-primary-lucebox-ds4.md

docs: distill the managed skill library into the vault (waves 1-7)

2026-10-05 21:19:15 -07:00

frank-primary-r9v-radiance-qwen38-q8.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-primary-r9v-radiance-qwen38-uncensored.md

docs: frank-primary q8 cutover — new runbook, uncensored retired as rollback, fleet table/index/log synced

2026-09-27 22:53:19 -07:00

frank-primary-radiance-qwen38-native-fp8.md

radiance runbook: MNBT A/B verdict + rad-tune tune-dir bind-mount

2026-10-06 03:08:30 -07:00

frank-primary-radiance-swift15-w4dn8.md

docs: record the wire rename, the OpenWebUI re-key, and the frank-primary bench drop-in trap

2026-10-09 17:06:44 -07:00

frank-redo-2026-08-17.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-secondary-benchmark.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-secondary-gemma4-12b.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-secondary-llama-gemma4-q4km-200704.md

frank-secondary: swap Gemma4-26B-A4B Q4_K_M -> Qwen3.5-9B-Uncensored Q6_K 2x200,704

2026-10-07 14:47:32 -07:00

frank-secondary-llama-mimo-q5km.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-secondary-llama-mimo-q6k-2x200704.md

docs: frank-secondary at 2x114688/ubatch 1024 — runbook renamed + rewritten, fleet docs updated

2026-10-06 18:13:05 -07:00

frank-secondary-llama-mimo-q6k.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-secondary-llama-qwen35-9b-q6k-2x200704.md

docs: record the wire rename, the OpenWebUI re-key, and the frank-primary bench drop-in trap

2026-10-09 17:06:44 -07:00

frank-secondary-llama-swift15-unc-iq3xxs-mtp-114688.md

docs: frank-secondary at ubatch 2048 — Measured section, rollback ladder, fleet docs

2026-10-06 18:40:26 -07:00

frank-secondary-qwen38-gsq-rco.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-secondary-sglang-mimo-v26.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

frank-secondary-vllm-gemma4.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

FreeToken Builds.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

freetoken-benchmark-sweep.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

freetoken-frank-small.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

GGUF Compatibility.md

docs: vault link integrity restored after rogue-session doc WIP landed

2026-10-05 18:40:31 -07:00

halogen-flash-server.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

Heterogeneous Split Triage.md

docs: distill the managed skill library into the vault (waves 1-7)

2026-10-05 21:19:15 -07:00

Hybrid CPU GPU Processing Dankserver.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

ikllama-ornith-dankserver.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

index.md

docs(LLM): Quantization Production reference — per-card self-quant playbooks, REAP/Heretic/abliteration/K_P prior art

2026-10-08 22:39:18 -07:00

kairic-edge.md

docs: rename frank-default-large/small/sightsound to frank-large/small/npu across vault

2026-09-03 16:17:14 -07:00

kingjones-q8agent-rocmfpx.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

kingjones-strix-mtp.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

kingjones-strix-rocmfp4.md

feat(llm): swap frank-large to halogen-flash-server, retire frank-npu

2026-09-11 14:48:28 -07:00

ling-3.0-flash-trial.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

ling-3.0-flash-vllm-plan.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

Llama Cpp Multi-Device Splits.md

docs: vault link integrity restored after rogue-session doc WIP landed

2026-10-05 18:40:31 -07:00

Llama Cpp Serving Sizing.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

LLM Bench Windows and Measurement.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

LLM Performance Diagnosis.md

docs: distill the managed skill library into the vault (waves 1-7)

2026-10-05 21:19:15 -07:00

Model Swap and Rollback.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

PCIe Link and Atomics.md

docs: vault link integrity restored after rogue-session doc WIP landed

2026-10-05 18:40:31 -07:00

Quantization by Hardware Architecture.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

Quantization Production.md

docs(LLM): 3090 worked example — archon w4dn8 methodology ports to GGUF-native quants; 24 GiB size law for 35B-A3B

2026-10-08 23:44:13 -07:00

qwen3.8-spec-matrix.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

qwen3.8-strix-optimizations.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

RAM CPU Offloading in VLLM.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

RDNA4 Container Serving.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

RDNA4 MoE Expert Offload VRAM Budget.md

docs: vault link integrity restored after rogue-session doc WIP landed

2026-10-05 18:40:31 -07:00

Running Qwen3.6 27B FP8 on Dankclaw.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

Running Qwen3.6 35B A3B FP8 on Dankserver.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

Shared Memory Architecture Dankclaw.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

swift15-campaign-worklog.md

docs(worklog): KLD reference complete (rows 50235), script-swap law third occurrence

2026-10-07 02:49:14 -07:00

Tcclaviger Fork Ops.md

docs: distill the managed skill library into the vault (waves 1-7)

2026-10-05 21:19:15 -07:00

ubatch-benchmark-large.md

docs: rename frank-default-large/small/sightsound to frank-large/small/npu across vault

2026-09-03 16:17:14 -07:00

vLLM Boot Forensics and Config Interrogation.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

VLLM Index.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

VLLM Overview.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00

vLLM Porting and Compile Triage.md

docs: vault link integrity restored after rogue-session doc WIP landed

2026-10-05 18:40:31 -07:00

vllm_research_findings.md

docs: OKF v0.1 compliance pass + fact-check + 3 research briefs

2026-09-22 02:09:41 -07:00

x4-pair-experiment.md

rename frank-small → frank-secondary (Dankclaw llama.cpp :7771)

2026-10-06 15:37:13 -07:00