Hitonabi
e2547ec301
llama-server lehnt --prompt-cache/--prompt-cache-all ab ("invalid argument")
und startet dann nicht — dadurch ließ sich KEIN Modell mehr wecken (u.a. das
Hermes-WebUI bekam "empty stream"). Die Flags gehören zu llama-cli, nicht zum
Server; Prompt-Caching macht llama-server automatisch pro Slot (KV-Reuse).
- config.py: Flags aus _DEFAULT_CMD_TEMPLATE entfernt (+ Warnhinweis).
- migrate_config.py: statt die Flags hinzuzufügen, entfernt es sie nun aus
bestehenden cmds (Reparatur-Migration).
Box-config.yaml wurde bereits direkt korrigiert (alle 7 Modelle); verifiziert:
Hermes lädt + streamt wieder sauber.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
56 lines
1.8 KiB
Python
56 lines
1.8 KiB
Python
import sys
|
|
from pathlib import Path
|
|
|
|
# Add backend directory to sys.path so we can import services
|
|
sys.path.append(str(Path(__file__).resolve().parent))
|
|
|
|
from services.llamaswap import read_config, write_config
|
|
from config import CONFIG_PATH, SPEC_DRAFT_MODEL_PATH
|
|
|
|
def migrate():
|
|
print(f"Reading config from {CONFIG_PATH}...")
|
|
if not CONFIG_PATH.exists():
|
|
print(f"Config path {CONFIG_PATH} does not exist. Skipping.")
|
|
return
|
|
|
|
cfg = read_config()
|
|
models = cfg.get("models", {})
|
|
|
|
draft_path = SPEC_DRAFT_MODEL_PATH
|
|
|
|
for name, spec in models.items():
|
|
if not isinstance(spec, dict):
|
|
continue
|
|
cmd = spec.get("cmd", "")
|
|
if not cmd:
|
|
continue
|
|
|
|
print(f"Migrating model: {name}")
|
|
|
|
# 1. Defektes --prompt-cache/--prompt-cache-all entfernen (llama-CLI-Flags,
|
|
# die llama-server ablehnt → Start scheitert). Caching macht llama-server
|
|
# automatisch pro Slot.
|
|
cmd = cmd.replace(" --prompt-cache-all", "").replace(" --prompt-cache", "")
|
|
|
|
# 2. Extract aliases/role
|
|
aliases = spec.get("aliases", [])
|
|
role = aliases[0] if aliases else None
|
|
|
|
# 3. Add parallel and speculative decoding for fast and coder
|
|
if role in ("fast", "coder"):
|
|
if "--parallel" not in cmd:
|
|
cmd = cmd.strip() + " --parallel 2"
|
|
if "--spec-draft-model" not in cmd:
|
|
cmd = cmd.strip() + f" --spec-draft-model {draft_path}"
|
|
|
|
# Update cmd
|
|
from ruamel.yaml.scalarstring import LiteralScalarString
|
|
spec["cmd"] = LiteralScalarString(cmd.strip() + "\n")
|
|
|
|
print(f"Writing updated config back to {CONFIG_PATH}...")
|
|
write_config(cfg)
|
|
print("Migration completed successfully!")
|
|
|
|
if __name__ == "__main__":
|
|
migrate()
|