Frank a4fe5f6839 fix(frank-zealot): serve /metrics so Prometheus can see the endpoint ...

The scrape has never worked: lastError is "server returned HTTP status 501 Not
Implemented" on http://host.containers.internal:7771/metrics, and the oldest
retained sample of up{job="frank-zealot"} (2026-10-11) is already 0 -- the target
has been red across four payload generations while /health answered 200 the whole
time, keeping the critical LlmEndpointDown alert permanently active. llama.cpp
gates /metrics behind --metrics; halogen serves it natively, which is why the
asymmetry looked like a 3090-only problem.

METRICS=1 in the shipped env, --metrics reaches the argv through EXTRA_ARGS, and
the seam asserts both directions (default ships the flag, METRICS=0 strips it).
Diagnosed via /api/v1/targets lastError rather than the alert list, which is also
the lesson: Alertmanager here has no persistence, so a reboot re-stamps startsAt
and a weeks-old fault looks fresh.

2026-10-18 01:52:19 -07:00

..

Pipeline Parallelism

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

agentionai-fast-imatrix.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

ciru-activefpx-promptforge.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

Dankclaw Improvements.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

Dankclaw System Specs.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

dankclaw-iommu-translation-off.md

docs(iommu): record the executed flip to iommu=pt and its measured cost of nothing

2026-10-18 01:34:17 -07:00

Dankserver System Specs.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

dankserver-frontier-moe-feasibility.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

dankserver-vram-growth.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

dealign-ornith-crack.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

deployment.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

dflash2-large-vulkan.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

DFlash DSpark Speculative Decoding.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

FastFlowLM NPU Inference.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-archon-freetoken-pr587.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-archon-glm53-flash-w4a16.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-archon-lucebox-ds4.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-archon-radiance-qwen38-iq4r.md

docs(frank-archon): rollback re-key after 2026-10-17 disk purge

2026-10-17 21:00:26 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-archon-radiance-swift15-w4dn8.md

docs(frank-archon): rollback re-key after 2026-10-17 disk purge

2026-10-17 21:00:26 -07:00

frank-dragoon-benchmark.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-dragoon-ciru-orca.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-dragoon-flash-server-v2-native.md

e2e: crawl reset survives app navigation; dragoon docs carry the cut ledger

2026-10-17 22:45:34 -07:00

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

docs(frank-dragoon): native-era runbook; retire the swift15 page

2026-10-17 22:18:00 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-dragoon-halogen27b-dflash2.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-dragoon-ik-uncensored.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-dragoon-rocmfpx-q8agent-mtp.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-medium-batch-ubatch.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-medium-llamacpp-dflash2.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-medium-rocmfpx.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-npu.md

docs(iommu): record the executed flip to iommu=pt and its measured cost of nothing

2026-10-18 01:34:17 -07:00

frank-redo-2026-08-17.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-zealot-benchmark.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-zealot-gemma4-12b.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-zealot-llama-mimo-q5km.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-zealot-llama-mimo-q6k.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-zealot-llama-prism-bonsai2-pq20.md

fix(frank-zealot): serve /metrics so Prometheus can see the endpoint

2026-10-18 01:52:19 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-zealot-qwen38-gsq-rco.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-zealot-sglang-mimo-v26.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

frank-zealot-vllm-gemma4.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

FreeToken Builds.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

freetoken-benchmark-sweep.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

freetoken-frank-small.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

GGUF Compatibility.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

halogen-flash-server.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

index.md

docs(iommu): record the executed flip to iommu=pt and its measured cost of nothing

2026-10-18 01:34:17 -07:00

kairic-edge.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

kingjones-q8agent-rocmfpx.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

kingjones-strix-mtp.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

kingjones-strix-rocmfp4.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

ling-3.0-flash-trial.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

ling-3.0-flash-vllm-plan.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

LLM Bench Windows and Measurement.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

LLM Performance Diagnosis.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

Model Swap and Rollback.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

qwen3.8-spec-matrix.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

qwen3.8-strix-optimizations.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

RDNA4 MoE Expert Offload VRAM Budget.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

Running Qwen3.6 27B FP8 on Dankclaw.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

Tcclaviger Fork Ops.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

ubatch-benchmark-large.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

vLLM Boot Forensics and Config Interrogation.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00

vLLM Porting and Compile Triage.md

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -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

llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

2026-10-10 17:03:14 -07:00