feat(llm): rename inference services dropping 'default' from names
frank-default-large -> frank-large (Dankclaw :7770), frank-default-small -> frank-small (Dankserver :7770), frank-default-sightsound -> frank-npu (Dankclaw :7771). Units, env files, serve scripts, deploy-plan mappings, deploy-remote dispatch (stop/disable old units + relink + enable new), and the test seams move together. Retired frank-default-npu.* artifacts moved to scripts/.AGENTTRASH/ (tracked-in-history; ignored on disk). Served aliases become frank-large / frank-small via --alias; the NPU endpoint serves the whole FLM registry, so its rename changes no served tags.
This commit is contained in:
1 parent
1e491fa69f
commit
69f87c8483
34 files changed
+136
-137
No files matched your search
@@ -1,6 +1,6 @@
|
||||
#!/usr/bin/env bash
|
||||
# Serve kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF as
|
||||
# frank-default-large via the kingjones30/ROCmFPX llama.cpp runtime on
|
||||
# frank-large via the kingjones30/ROCmFPX llama.cpp runtime on
|
||||
# Dankclaw (Strix Halo gfx1151, unified memory).
|
||||
#
|
||||
# Runtime: kingjones30/ROCmFPX (fork of charlie12345/ROCmFPX with the
|
||||
@@ -29,7 +29,7 @@
|
||||
set -euo pipefail
|
||||
|
||||
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
|
||||
ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-default-large.env}"
|
||||
ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-large.env}"
|
||||
if [[ -f "$ENV_FILE" ]]; then
|
||||
set -a
|
||||
# shellcheck disable=SC1090
|
||||
@@ -44,7 +44,7 @@ fi
|
||||
: "${MMPROJ_PATH:=/home/dank/models/agentionai-Qwen3.8-Flash-Next-ROCmFP4-FAST/mmproj/mmproj-Qwen3.8-Flash-Next-f16.gguf}"
|
||||
: "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
|
||||
: "${CHAT_TEMPLATE_KWARGS:={}}"
|
||||
: "${ALIAS:=frank-default-large}"
|
||||
: "${ALIAS:=frank-large}"
|
||||
: "${BIND_ADDR:=0.0.0.0}"
|
||||
: "${LISTEN_PORT:=7770}"
|
||||
: "${CTX_SIZE:=401408}"
|
||||
|
||||
Reference in new issue
Block a user