* Optimize transformer int4 loading memory * move cast to convert * default settting low_cpu_mem_usage |
||
|---|---|---|
| .. | ||
| llm | ||
| __init__.py | ||
* Optimize transformer int4 loading memory * move cast to convert * default settting low_cpu_mem_usage |
||
|---|---|---|
| .. | ||
| llm | ||
| __init__.py | ||