dank/serverAppConfigs
1
0
Fork 0
Code Issues 6 Pull Requests Actions Packages Projects Releases Wiki Activity

docs(vault): documentation exists for point of use — destroy the ledgers (−13.7k lines) #31

Merged
dank merged 13 commits from docs/vault-destruction-20261019 into main 2026-10-19 10:59:51 -07:00
Conversation 0 Commits 13 Files Changed 157
+2 -2
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit c860fb3c8c - Show all commits
serverAppConfigs-docs/LLM/frank-medium.md
+2 -2
View File
@@ -26,10 +26,10 @@ Windows are quoted from each era page's own banner; no date here is derived.
| Window | Runtime | Payload | Shape | Page | Rollback |
|---|---|---|---|---|---|
| 2026-09-15 → 2026-09-16 | llama.cpp, ROCmFPX fork pinned at commit `36e9acd` | `Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf` (custom tensor type 103) | single card; the fork is the only loader | [[frank-medium-rocmfpx]] | re-fetch the GGUF, rebuild the fork |
| 2026-09-15 → 2026-09-16 | `charlie12345/ROCmFPX` llama.cpp `main` at `c49ebdb`, self-contained ROCm 7.14 | `Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf` (custom tensor type 103) + an MTP Q4_0 draft | 2× R9700 `-sm layer` over `ROCm0,ROCm1`, 131,072 × 1 slot, f16 KV + flash attention, draft-MTP pinned to `ROCm1`; the fork is the only loader for that tensor type | [[frank-medium-rocmfpx]] | re-fetch the GGUF, rebuild the fork |
| 2026-09-16 → 2026-09-19 | vllm-radiance on the old TUF GAMING B650-E board | ParoQuant MXFP4 | two single-GPU replicas behind an adaptive-routing proxy | [[frank-medium-radiance-mxfp4]] (sections below its deployed-shape header) | the replica pair is reconstructable from that page's flags |
| 2026-09-16 → 2026-09-20 | llama.cpp `fb27a525`, ROCm `7.14.0a` | its own GGUF build, DFlash drafter | `-sm layer` split across the two cards, drafter pinned to one device | [[frank-medium-llamacpp-dflash2]] | the page is the named rollback target for the llama shape |
| 2026-09-20 → disputed, see Open questions | vllm-radiance on the replacement ProArt board | ParoQuant MXFP4, then MXFP6 (`paroquant_mxfp6`) with bf16 KV | `--tensor-parallel-size 2` over x8/x8 Gen5 root ports | [[frank-medium-radiance-mxfp4]] (deployed-shape header) | re-fetch the MXFP4 checkpoint (host census 2026-10-19: not local); image `localhost/radiance-vllm:0.9.3` |
| 2026-09-20 → disputed, see Open questions | vllm-radiance on the replacement ProArt board | ParoQuant MXFP4 → FP8 E4M3 128×128 (`orcarouter/…-FP8`, same day, [[frank-medium-model-swap]]) → ParoQuant MXFP6 (`paroquant_mxfp6`) from 09-21 | `--tensor-parallel-size 2` over x8/x8 Gen5 root ports | [[frank-medium-radiance-mxfp4]] (deployed-shape header) | re-fetch the MXFP4 checkpoint (host census 2026-10-19: not local); image `localhost/radiance-vllm:0.9.3` |
`[[frank-medium-batch-ubatch]]` is not an era: it is the batch-versus-ubatch sweep run
on the layer-split pair at its deployed shape, and its numbers belong to that