Frank c1a4ccbbcd feat(frank-medium): swap MXFP4 -> FP8; add the one-command swap toolchain ...

Checkpoint: just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq ->
orcarouter/Qwen3.8-27B-Uncensored-FP8 (FP8 E4M3 block-wise, 30.9 GB / 7
shards, its own single-layer MTP head). The quantization-aware entrypoint
serves the plain FP8 path: --quantization fp8, ROCM_AITER_UNIFIED_ATTN, MTP
self-speculation (SPEC_METHOD=mtp, SPEC=8). Measured: MTP mean accept 5.66/8
(66.2% draft acceptance), KV pool auto-sized to 461,540 tokens (1.76x),
battery 85.9 t/s decode / 0.06 s TTFT / 179.7 burst-4 (vs MXFP4 92.4/0.22/
248.9). MXFP4 checkpoint stays on disk as the rollback target.

Streamlining: scripts/hf-manifest.py (generate a <filename> <size> <sha256>
manifest from the live repo tree), scripts/hf-fetch.sh (resumable, byte +
sha256 verified, idempotent fetch), scripts/swap-frank-medium.sh (generate
manifest -> download -> detect quantization -> edit the quadlet -> deploy).

Docs: new frank-medium-model-swap runbook; radiance runbook, both indexes,
AGENTS.md, and log.md flipped to the FP8 shape.

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

..

Pipeline Parallelism

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

2026-09-03 16:17:14 -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: rename frank-default-large/small/sightsound to frank-large/small/npu across vault

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

Dankclaw Improvements.md

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

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

Dankclaw System Specs.md

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

2026-09-03 16:17:14 -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

docs: dankserver board swap clears the PCIe-atomics wall

2026-09-20 14:39:54 -07:00

dankserver-vram-growth.md

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

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

dealign-ornith-crack.md

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

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

deployment.md

docs: the vault and AGENTS.md describe two Dankclaw endpoints

2026-09-16 14:52:51 -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

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

2026-09-03 16:17:14 -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

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

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

FastFlowLM NPU Inference.md

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

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

frank-large-benchmark.md

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

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

frank-large-ciru-orca.md

docs: wrap up the 2026-09-19 fleet cutover

2026-09-19 06:12:33 -07:00

frank-large-ik-uncensored.md

docs: the vault and AGENTS.md describe two Dankclaw endpoints

2026-09-16 14:52:51 -07:00

frank-medium-batch-ubatch.md

docs: the ubatch optimum, the rebalance, and the live atomics chain

2026-09-17 00:27:59 -07:00

frank-medium-llamacpp-dflash2.md

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

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

frank-medium-model-swap.md

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

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

frank-medium-radiance-mxfp4.md

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

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

frank-medium-rocmfpx.md

docs: frank-medium is llama.cpp with DFlash2 on both cards

2026-09-16 15:15:02 -07:00

frank-npu.md

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

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

frank-redo-2026-08-17.md

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

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

frank-small-benchmark.md

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

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

frank-small-gemma4-12b.md

docs: the max-length sweep tabled; frank-small.env NGL/FLASH_ATTN restored

2026-09-17 04:56:59 -07:00

frank-small-qwen38-gsq-rco.md

docs: frank-small is Gemma4-12B QAT now — new runbook, Qwen retired as rollback target

2026-09-17 02:18:44 -07:00

frank-small-vllm-gemma4.md

frank-small: llama.cpp -> vLLM (gemma-4-12B-it-qat-w4a16-ct, w4a16 Marlin)

2026-09-18 21:06:46 -07:00

freetoken-benchmark-sweep.md

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

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

freetoken-frank-small.md

docs: frank-medium runbook, fleet topology and client cutover

2026-09-15 19:27:04 -07:00

halogen-flash-server.md

docs: frank-medium deployed-flags table + halogen retirement banner

2026-09-19 06:20:57 -07:00

Hybrid CPU GPU Processing Dankserver.md

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

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

ikllama-ornith-dankserver.md

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

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

index.md

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

2026-09-20 21:53:00 -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: frank-medium runbook, fleet topology and client cutover

2026-09-15 19:27:04 -07:00

kingjones-strix-mtp.md

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

2026-09-03 16:17:14 -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: rename frank-default-large/small/sightsound to frank-large/small/npu across vault

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

ling-3.0-flash-vllm-plan.md

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

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

Quantization by Hardware Architecture.md

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

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

qwen3.8-spec-matrix.md

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

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

qwen3.8-strix-optimizations.md

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

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

RAM CPU Offloading in VLLM.md

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

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

Running Qwen3.6 27B FP8 on Dankclaw.md

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

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

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

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

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

Shared Memory Architecture Dankclaw.md

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

2026-08-28 02:20:06 -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 Index.md

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

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

VLLM Overview.md

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

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

vllm_research_findings.md

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

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

x4-pair-experiment.md

the x4 link, measured: 6.72 GB/s — which decides the streaming question

2026-09-16 23:25:06 -07:00