frank-primary: cutover state to Qwen3.8-Flash-Next Q8_0 (6 shards, PLE pinned, MTP4, sharp template)
- env: STATE_FILE -> r9v-state/q8xl; add dev-overlay adapter mount (quantized inject shard dequant, fork 363d606), FULL_MUTABLE_CACHE=0 (80-slot tiered vs the overlay's uncensored 160-slot injection), and the qwen-sharp-v22.4.0.jinja chat template via the launcher's new R9V_CHAT_TEMPLATE_FILE/KWARGS passthrough (fork 30d4a32) - serve/deploy: shard gates extended to SHARD4/5/6 (unset-safe, the uncensored rollback state carries none) - seams: STATE_FILE/LLM_PRIMARY_STATE -> q8xl
This commit is contained in:
1 parent
928fd81dbd
commit
b06895d725
4 files changed
+61
-30
No files matched your search
@@ -65,11 +65,11 @@ REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
|
||||
}
|
||||
|
||||
@test "the tuned engine shape comes from the on-host setup state, not the repo" {
|
||||
# The profile setup qualified a 104-key shape (tiered-expert placement,
|
||||
# per-rank offload budgets, CED, MTP4, parser wiring). Copying it into
|
||||
# The profile setup qualified the tuned shape (tiered-expert placement,
|
||||
# per-rank offload budgets, MTP4, parser wiring). Copying it into
|
||||
# the repo would drift; the serve script layers it and skips keys the
|
||||
# env file defines, so production overrides always win.
|
||||
grep -q 'R9V_STATE_FILE=/home/dank/r9v-state/uncensored/setup.json' "$ENV_FILE"
|
||||
grep -q 'R9V_STATE_FILE=/home/dank/r9v-state/q8xl/setup.json' "$ENV_FILE"
|
||||
grep -q 'state must carry R9V_MODEL_DIR' "$SERVE"
|
||||
grep -q 'is not ready' "$SERVE"
|
||||
grep -q 'key not in env_keys' "$SERVE"
|
||||
@@ -122,7 +122,7 @@ REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
|
||||
# the PLE payload is off its pinned byte count, or when any GGUF shard
|
||||
# or the mmproj is missing — then clears stale containers, waits out
|
||||
# the port, relinks/enables/restarts the root unit and health-gates it.
|
||||
grep -q 'LLM_PRIMARY_STATE=/home/dank/r9v-state/uncensored/setup.json' "$REMOTE_DEPLOY"
|
||||
grep -q 'LLM_PRIMARY_STATE=/home/dank/r9v-state/q8xl/setup.json' "$REMOTE_DEPLOY"
|
||||
grep -q 'LLM_PRIMARY_CONTAINER=frank-primary-r9v' "$REMOTE_DEPLOY"
|
||||
grep -q 'is not ready' "$REMOTE_DEPLOY"
|
||||
grep -q "podman images --format '{{.RepoDigests}}'" "$REMOTE_DEPLOY"
|
||||
|
||||
Reference in new issue
Block a user