Reorganize: llm/docs -> docs/LLM (LLM fleet knowledge base)

Browse Source

The LLM fleet documentation (deployment runbook, model runbooks,
benchmarks, research archive, retired-topology history) joins the
project knowledge base as docs/LLM/. Wikilinks resolve by filename,
so no link updates are needed for the move.

...

This commit is contained in:

Frank

2026-08-22 15:06:51 -07:00

parent 918fe4eaec

commit 017d3704d2

36 changed files with 0 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

llm/docs/DFlash DSpark Speculative Decoding.md → docs/LLM/DFlash DSpark Speculative Decoding.md

llm/docs/Dankclaw Improvements.md → docs/LLM/Dankclaw Improvements.md

llm/docs/Dankclaw System Specs.md → docs/LLM/Dankclaw System Specs.md

llm/docs/Dankserver System Specs.md → docs/LLM/Dankserver System Specs.md

llm/docs/FastFlowLM NPU Inference.md → docs/LLM/FastFlowLM NPU Inference.md

llm/docs/Hybrid CPU GPU Processing Dankserver.md → docs/LLM/Hybrid CPU GPU Processing Dankserver.md

llm/docs/Pipeline Parallelism/Ethernet Bandwidth Math.md → docs/LLM/Pipeline Parallelism/Ethernet Bandwidth Math.md

llm/docs/Pipeline Parallelism/Expected Performance.md → docs/LLM/Pipeline Parallelism/Expected Performance.md

llm/docs/Pipeline Parallelism/Mixed-Vendor Experiments.md → docs/LLM/Pipeline Parallelism/Mixed-Vendor Experiments.md

llm/docs/Pipeline Parallelism/Qwen3.6 27B Spec Methods.md → docs/LLM/Pipeline Parallelism/Qwen3.6 27B Spec Methods.md

llm/docs/Pipeline Parallelism/Qwen3.8 PP Deployment.md → docs/LLM/Pipeline Parallelism/Qwen3.8 PP Deployment.md

llm/docs/Pipeline Parallelism/Sample Script Set.md → docs/LLM/Pipeline Parallelism/Sample Script Set.md

llm/docs/Pipeline Parallelism/index.md → docs/LLM/Pipeline Parallelism/index.md

llm/docs/Pipeline Parallelism/llama.cpp RPC.md → docs/LLM/Pipeline Parallelism/llama.cpp RPC.md

llm/docs/Pipeline Parallelism/vLLM Pipeline Parallelism.md → docs/LLM/Pipeline Parallelism/vLLM Pipeline Parallelism.md

llm/docs/Quantization by Hardware Architecture.md → docs/LLM/Quantization by Hardware Architecture.md

llm/docs/RAM CPU Offloading in VLLM.md → docs/LLM/RAM CPU Offloading in VLLM.md

llm/docs/Running Qwen3.6 27B FP8 on Dankclaw.md → docs/LLM/Running Qwen3.6 27B FP8 on Dankclaw.md

llm/docs/Running Qwen3.6 35B A3B FP8 on Dankserver.md → docs/LLM/Running Qwen3.6 35B A3B FP8 on Dankserver.md

llm/docs/Shared Memory Architecture Dankclaw.md → docs/LLM/Shared Memory Architecture Dankclaw.md

llm/docs/VLLM Index.md → docs/LLM/VLLM Index.md

llm/docs/VLLM Overview.md → docs/LLM/VLLM Overview.md

llm/docs/ciru-activefpx-promptforge.md → docs/LLM/ciru-activefpx-promptforge.md

llm/docs/dankserver-vram-growth.md → docs/LLM/dankserver-vram-growth.md

llm/docs/deployment.md → docs/LLM/deployment.md

llm/docs/dflash2-large-vulkan.md → docs/LLM/dflash2-large-vulkan.md

llm/docs/frank-default-large-benchmark.md → docs/LLM/frank-default-large-benchmark.md

llm/docs/frank-default-small-benchmark.md → docs/LLM/frank-default-small-benchmark.md

llm/docs/frank-redo-2026-08-17.md → docs/LLM/frank-redo-2026-08-17.md

llm/docs/index.md → docs/LLM/index.md

llm/docs/kairic-edge.md → docs/LLM/kairic-edge.md

llm/docs/ling-3.0-flash-trial.md → docs/LLM/ling-3.0-flash-trial.md

llm/docs/ling-3.0-flash-vllm-plan.md → docs/LLM/ling-3.0-flash-vllm-plan.md

llm/docs/qwen3.8-spec-matrix.md → docs/LLM/qwen3.8-spec-matrix.md

llm/docs/qwen3.8-strix-optimizations.md → docs/LLM/qwen3.8-strix-optimizations.md

llm/docs/vllm_research_findings.md → docs/LLM/vllm_research_findings.md