fix(litellm): remove the trial alias — run 7 failed the safety gate
Alias-present-with-backend-down is a different and worse state than alias-removed: it re-arms silently the moment anything is served on 10.250.50.54:8021 again, and the next thing served there inherits a fleet-reachable name without anyone deciding it should. Flagged by brokkr-smithy-dev; same writer/reader-contract family as ops-lessons §11. Commented rather than deleted so restoring is uncommenting, not reconstructing. Verified: /v1/models returns 33 entries, trial absent, a caller gets a clean 400 'Invalid model name' instead of a connection error to a port that could re-arm. Disposition of the artifact and the alias is the operator's.
This commit is contained in:
@@ -882,11 +882,30 @@ model_list:
|
||||
#
|
||||
# Same-site: seat and gateway are both at Anaheim (local hop, no mesh crossing).
|
||||
|
||||
- model_name: trial
|
||||
litellm_params:
|
||||
model: hosted_vllm/erp-tune-v7-nvfp4a16
|
||||
api_base: http://10.250.50.54:8021/v1
|
||||
api_key: os.environ/VLLM_API_KEY
|
||||
# ⚠ REMOVED 2026-09-09 17:5x PT — run 7 FAILED brokkr's CSAM safety gate
|
||||
# (detector fired on the tuned arm, fail-closed). The ana-ml2:8021 seat serving
|
||||
# the NVFP4 quant of that tune was stopped at 17:43; this alias is commented
|
||||
# out rather than left pointing at a dead port because ALIAS-PRESENT-WITH-
|
||||
# BACKEND-DOWN IS A DIFFERENT AND WORSE STATE THAN ALIAS-REMOVED: it re-arms
|
||||
# silently the moment anything is served on that port again, and the next
|
||||
# thing served there would inherit a fleet-reachable name without anyone
|
||||
# deciding it should. (brokkr-smithy-dev flagged the state; the reasoning is
|
||||
# the same writer/reader-contract family as ops-lessons §11.)
|
||||
#
|
||||
# The quant is rejected BY PROVENANCE — it descends from an artifact that
|
||||
# failed. Its OWN behaviour on the flagged axis is UNMEASURED and nothing here
|
||||
# claims otherwise.
|
||||
#
|
||||
# Commented, not deleted, so restoring is uncommenting rather than
|
||||
# reconstructing. Disposition of the artifact and of this alias is the
|
||||
# OPERATOR'S. If it returns, erp-tune-v6-nvfp4a16 is still on disk and passed
|
||||
# by his own adjudication — the obvious rollback target.
|
||||
#
|
||||
# - model_name: trial
|
||||
# litellm_params:
|
||||
# model: hosted_vllm/erp-tune-v7-nvfp4a16
|
||||
# api_base: http://10.250.50.54:8021/v1
|
||||
# api_key: os.environ/VLLM_API_KEY
|
||||
|
||||
general_settings:
|
||||
master_key: os.environ/LITELLM_MASTER_KEY
|
||||
|
||||
Reference in New Issue
Block a user