Frank 374041cd7a frank-small: revert vLLM cutover — back to llama.cpp Gemma4-12B Q4_K_M ...

The vLLM detour (a2b39b1, same day) is retired: the Q4_K_M llama.cpp setup
is the requested shape and the vLLM KV-quant options on sm_86 all measured
dead (fp8 hardware-impossible, int8 page-size unification, turboquant
mm-prefix). Root unit restored, vLLM quadlet/Dockerfile/fetch script moved
to .AGENTTRASH, runbook listed as same-day-reverted. Rollback target:
frank-small-vllm-gemma4.

2026-09-19 01:42:37 -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: frank-medium runbook, fleet topology and client cutover

2026-09-15 19:27:04 -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

frank-medium: ubatch 512, and rebalance the split to 35:30

2026-09-17 00:21:48 -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-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

docs: frank-medium prompt cache -- why the cap is load-bearing, and the vision correction

2026-09-18 15:57:25 -07:00

frank-medium-radiance-mxfp4.md

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

2026-09-16 15:15:02 -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: halogen 400-zone note (compaction gap vs fit check); chore: gitignore third_party/ fork tree against peer stash sweeps

2026-09-17 13:14:51 -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

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

2026-09-19 01:42:37 -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