- Replaced old KVCage API with PageCache/ContiguousCache - Added --cache contiguous|paged switch for decoding comparison - Added argparse for all params (batch/prompt/gen/device/dtype) - Fixed PageCache decode crash by extending pages for full sequence |
||
|---|---|---|
| .. | ||
| benchmark.py | ||
| generate.py | ||
| preprocess.py | ||
| server.py | ||
| train.py | ||