Allow serve-profile generation for models whose trained context window is below 8192 while preserving the 8K shrink floor for larger models. |
||
|---|---|---|
| .. | ||
| docs | ||
| faces | ||
| hwfit | ||
| memory | ||
| research | ||
| search | ||
| shell | ||
| stt | ||
| tts | ||
| youtube | ||
| __init__.py | ||
Allow serve-profile generation for models whose trained context window is below 8192 while preserving the 8K shrink floor for larger models. |
||
|---|---|---|
| .. | ||
| docs | ||
| faces | ||
| hwfit | ||
| memory | ||
| research | ||
| search | ||
| shell | ||
| stt | ||
| tts | ||
| youtube | ||
| __init__.py | ||