• Your Name's avatar
    Fix offload-strategy parameter passing to CUDA backend · bf1d3f52
    Your Name authored
    - Add offload_strategy to kwargs in _load_default_model and _load_model_by_name
    - Fix parameter name: ram -> manual_ram_gb to match backend expectation
    - Also pass load_in_4bit, load_in_8bit, and max_gpu_percent
    bf1d3f52
Name
Last commit
Last update
..
cache Loading commit data...
__init__.py Loading commit data...
capabilities.py Loading commit data...
grammar.py Loading commit data...
manager.py Loading commit data...
parser.py Loading commit data...
templates.py Loading commit data...
tool_call_grammar.gbnf Loading commit data...
utils.py Loading commit data...