- Place ik's Trellis (IQ*_KT), IQK (IQ*_K), MXFP4, and dedicated fast KV type
Q8_KV in a single high->low bits-per-value table with ROCmFPX TurboQuant KV.
- Mark mainline-provided types (*), KV-native vs weight-family-reused-for-KV.
- Hadamard annotated as a transform on top of a base quant, not a row.
- bpw read from exact ggml block structs (QK_K=256, fp16 scale): type_size x 8 / QK,
verified against the struct comment "6.5625 bits per weight" and the trait table.
Notes where legacy nominal figures (4.0/4.25) diverge.
- AGENTS.md: add benchmark directive (use llama-bench / vllm bench; ask before
rolling your own).
Fan out subagents to compare mainline llama.cpp, charlie12345/ROCmFPX,
and ik_llama.cpp, then add their findings to the project knowledge base:
- docs/Research/Llama Cpp Runtimes.md (positioning + quantization + server fit)
- docs/Research/Llama Cpp Code Diff.md (code-level quant diff, table, recommendations)
- docs/Research/SGLang.md (what SGLang is, comparison, our-boxes fit)
- docs/Research/index.md (Research progressive-disclosure index)
Cross-linked from docs/index.md (root) and docs/LLM/index.md.
AGENTS.md:
- Add Documentation Authoring section: docs/ is an OKF bundle; point doc authors
at the canonical spec in the system-config knowledge base
(~/.pi/agent/docs/references/okf-spec.md), not the orphaned
docs/references/okf-spec.md; consolidate read-index/one-concept-per-file/
progressive-disclosure/citation rules.
- Map AGENTS.md to docs_completeness.bats in the focused pre-commit hook (it was
last committed before the hook existed and had no mapping).
Fanned out 5 read-only doc-auditor subagents (one per service group) that
fact-checked the knowledge base against the live system + repo config,
researched official setup docs online, and verified progress. Applied:
- All 34 broken links fixed (real pages / external URLs / correct relative
paths); 0 broken links remain. No .AGENTTRASH links (the 4 mentions are
accurate descriptive text, not links).
- Fact-check fixes: Readarr retired (May 2026), Radarr v4->v6, Calibre
9.2.1 live, Calibre-Web 0.6.25 live, Copyparty v1.20.21, LLM index
ncmoe 38 + 786432 ctx, frank-default-small active (not frank-pp-worker),
Hermes/SearXNG/Grafana hostnames, Loki/Alloy local images, Observability
diagram (Promtail->Alloy), VLLM retired note, DFlash status, benchmark
live-drift notes, Homepage test count 116.
Rewrite ComfyUI.md to match reality: comfyui-rocm:gfx1151 built from
Containerfile.comfyui on AMD's gfx1151 base, device passthrough, video group
only (render is unmappable in rootless), data under /home/dank/comfyui-data,
boot-persistent via a user systemd unit. Mark research 'way 1' as applied and
update the repo-consequence section (the CPU config is no longer the default).
Live-verified on Dankclaw 2026-08-14:
- official rocm/comfyui image is built PYTORCH_ROCM_ARCH=gfx942;gfx950
(datacenter only) -> torch.cuda.is_available() False on gfx1151
- AMD gfx1151-tagged PyTorch build (rocm/vllm:...gfx1151...pytorch_2.9.1)
-> avail True, Radeon 8060S, cap (11,5); needs /dev/kfd + /dev/dri
- torch.backends.vulkan is compiled out of standard wheels; no ComfyUI
--vulkan flag exists; Vulkan is a dead end for ComfyUI
- Lemonade Server does image gen via wrapped stable-diffusion.cpp, whose
HIP kernels include gfx1151 -> works where ComfyUI's torch cannot
New pages: ComfyUI ROCm and Vulkan, Lemonade and sd.cpp; ComfyUI.md
qualified; compose stays --cpu until a gfx1151-enabled torch image is built
Frank