Revert frank-default-large to CIRU runtime (DFlash2 too slow)

Restore the CIRU ROCmFPX setup that DFlash2 replaced:

- Restore jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge v2 runtime
  (native depth-4 MTP, PromptForge DualView, ROCm 7.15)
- Archive the DFlash2 Vulkan deployment files in .AGENTTRASH
- DFlash2 was retired the same day it shipped (2026-08-21) for speed
- Revert docs (deployment.md, index.md, AGENTS.md); mark dflash2 page archived
- Restored scripts are byte-identical to the pre-swap CIRU versions
This commit is contained in:
Frank committed 2026-08-21 10:15:23 -07:00
1 parent fd0d9dd3cb
commit 583efd8cf2
11 files changed
+316 -302

No files matched your search

+12 -13
View File
@@ -2,7 +2,7 @@
Documentation for the LLM inference fleet on two local machines
(2026-08-21): upstream llama.cpp on Dankserver (frank-default-small) and
upstream llama.cpp PR #27342 DFlash2 on Dankclaw (frank-default-large).
CIRU ROCmFPX llama.cpp on Dankclaw (frank-default-large).
## Deployment Topology
@@ -19,11 +19,10 @@ ngram-mod, 36 MoE experts on CPU, 700K ctx]
subgraph Dankclaw[AMD Strix Halo - Ubuntu 26.04]
D[gfx1151 iGPU 64 GiB unified memory]
E[upstream llama.cpp PR #27342 DFlash2, Vulkan
E[CIRU ROCmFPX llama.cpp
frank-default-large, port 52625]
F[unsloth Qwen3.8-27B-UD-Q8_K_XL +
z-lab Qwen3.8-27B-DFlash2-Q4_K_M drafter
262K ctx / 1 slot, DFlash2 spec]
F[jcbtc Qwen3.8-27B-CIRU-ActiveFPX-PromptForge
262K ctx / 1 slot, native MTP, PromptForge DualView]
D --> E --> F
end
@@ -42,20 +41,20 @@ z-lab Qwen3.8-27B-DFlash2-Q4_K_M drafter
- [[deployment]] — deploy and update process for both servers
- [[frank-redo-2026-08-17]] — the 2026-08-17 topology change
- [[dflash2-large-vulkan]] — the DFlash2 runtime on Dankclaw
(frank-default-large, Vulkan)
- [[ciru-activefpx-promptforge]] — the CIRU runtime on Dankclaw
(frank-default-large)
- [[Dankserver]] — the upstream llama.cpp box (frank-default-small)
- [[Dankclaw]] — the DFlash2 Vulkan box (frank-default-large)
- [[Dankclaw]] — the CIRU ROCmFPX box (frank-default-large)
## DFlash2 Reference (Dankclaw)
## CIRU Reference (Dankclaw)
- [[dflash2-large-vulkan]] — DFlash2 model, Vulkan build, build runbook,
- [[ciru-activefpx-promptforge]] — model, ROCm 7.15 toolchain, build,
and the frank-default-large service
## CIRU Reference (retired)
## DFlash2 Reference (archived)
- [[ciru-activefpx-promptforge]] — the retired CIRU ROCmFPX runtime
(archived in .AGENTTRASH, 2026-08-21)
- [[dflash2-large-vulkan]] — the retired DFlash2 Vulkan deployment
(2026-08-21)
## vLLM Reference (historical)