Frank fe34f04454 docs: record FreeToken compressed-tensors FP8 loader failures; Huihui restored ...

Ornith per-channel aborts in expert-source resolution (nonstandard
tensor naming); HauhauCS block-fp8 128x128 aborts in _dequant_fp8_weight
(shape mismatch). modelopt block-fp8 is the only FP8 path. Log entry +
runbook quant matrix updated; dead downloads staged to host trash.

2026-09-01 14:11:39 -07:00

..

Pipeline Parallelism

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

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

agentionai-fast-imatrix.md

docs: record fleet double swap (large -> kingjones STRIX on pinned fork, small -> Huihui FP8 on FreeToken)

2026-08-30 02:35:38 -07:00

ciru-activefpx-promptforge.md

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

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

Dankclaw Improvements.md

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

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

Dankclaw System Specs.md

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

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

Dankserver System Specs.md

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

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

dankserver-vram-growth.md

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

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

dealign-ornith-crack.md

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

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

deployment.md

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

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

dflash2-large-vulkan.md

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

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

DFlash DSpark Speculative Decoding.md

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

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

eemin-rocmi4-mtp.md

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

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

FastFlowLM NPU Inference.md

docs(sightsound): correct unknown-model-tag contract to live-probed behavior

2026-08-30 11:41:15 -07:00

frank-default-large-benchmark.md

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

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

frank-default-sightsound.md

docs: frank-default-sightsound runbook — model swap + tag switching

2026-09-01 01:53:59 -07:00

frank-default-small-benchmark.md

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

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

frank-redo-2026-08-17.md

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

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

freetoken-benchmark-sweep.md

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

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

freetoken-frank-default-small.md

docs: record FreeToken compressed-tensors FP8 loader failures; Huihui restored

2026-09-01 14:11:39 -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 docs/ -> serverAppConfigs-docs/ per system-wide PROJECTNAME-docs convention

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

index.md

sightsound: move FLM NPU endpoint port 52626 -> 7771

2026-08-30 14:06:54 -07:00

kairic-edge.md

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

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

kingjones-q8agent-rocmfpx.md

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

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

kingjones-strix-mtp.md

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

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

kingjones-strix-rocmfp4.md

docs: record fleet double swap (large -> kingjones STRIX on pinned fork, small -> Huihui FP8 on FreeToken)

2026-08-30 02:35:38 -07:00

ling-3.0-flash-trial.md

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

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

ling-3.0-flash-vllm-plan.md

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

2026-08-28 02:20:06 -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 docs/ -> serverAppConfigs-docs/ per system-wide PROJECTNAME-docs convention

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

qwen3.8-strix-optimizations.md

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

2026-08-28 02:20:06 -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 docs/ -> serverAppConfigs-docs/ per system-wide PROJECTNAME-docs convention

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

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

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

2026-08-28 02:20:06 -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 docs/ -> serverAppConfigs-docs/ per system-wide PROJECTNAME-docs convention

2026-08-28 02:20:06 -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