From 9cf4b1de8288bfa0fbc24b03f7d28a24099da533 Mon Sep 17 00:00:00 2001 From: Frank Date: Tue, 29 Sep 2026 23:51:53 -0700 Subject: [PATCH] docs: qwen-fp8 endpoint published on 7773; fix log bullet placement PORTMAP=7773:7770 hook; health 200 on 127.0.0.1 and 192.168.0.235, decode through the published path in band. 7773 chosen over 7770 (frank-primary owns 7770 when it returns). Log bullet recovered from a misplaced insert into the 2026-09-28 cleanup section. --- .../LLM/dankserver-qwen38-fp8-expert-offload-tuning.md | 7 +++++++ serverAppConfigs-docs/log.md | 6 ++++++ 2 files changed, 13 insertions(+) diff --git a/serverAppConfigs-docs/LLM/dankserver-qwen38-fp8-expert-offload-tuning.md b/serverAppConfigs-docs/LLM/dankserver-qwen38-fp8-expert-offload-tuning.md index e6cb6c2..a9ab7db 100644 --- a/serverAppConfigs-docs/LLM/dankserver-qwen38-fp8-expert-offload-tuning.md +++ b/serverAppConfigs-docs/LLM/dankserver-qwen38-fp8-expert-offload-tuning.md @@ -54,6 +54,13 @@ IMAGE=docker.io/tcclaviger/vllm@sha256:da4029666668b90a0386c1ed23ea370c79916ad4e # NO --expert-prefetch: measured 36% precision, ~50% wasted gather traffic ``` +Published to the host LAN via the serve script's `PORTMAP` hook +(`PORTMAP=7773:7770`): health and completions answer on +`http://192.168.0.235:7773` (verified host-side 2026-09-29; 256k config, +decode 36.49/34.55/35.98 through the published path). Host port 7773 was +chosen over 7770 because `frank-primary` (7770) is stopped but ENABLED — +any future start would collide with a published 7770. + Device notes carried from the bring-up: `--device /dev/dri` must be the WHOLE directory (individual renderD nodes enumerate but refuse contexts — "No CUDA GPUs are available" while device_count() reports 2); the image diff --git a/serverAppConfigs-docs/log.md b/serverAppConfigs-docs/log.md index 20b5752..7f9ef7d 100644 --- a/serverAppConfigs-docs/log.md +++ b/serverAppConfigs-docs/log.md @@ -131,6 +131,12 @@ is no longer referenced anywhere (the other image on the host, `28.06.1-Code000` = fffca39f, is a DIFFERENT build — do not confuse). Runbook deployment-shape section updated. + - **Endpoint published:** `PORTMAP=7773:7770` hook added to the serve + script; the 256k config relaunched with it. Host-side checks: health + 200 on 127.0.0.1:7773 AND 192.168.0.235:7773, /v1/models lists + qwen3.8-flash-next, decode through the published path + 36.49/34.55/35.98 (same band). 7773 chosen over 7770 — frank-primary + owns 7770 when it ever returns. ## 2026-09-28 - **Dankclaw model cleanup** (disk was at 93%, 137 G free). Frank asked to