| .. |
|
__init__.py
|
04b53d2db5
chore: add initializer files
|
1 gadu atpakaļ |
|
aphrodite_engine.py
|
a1f18f17e6
modify the cache engine and model runner/worker to support mamba states
|
8 mēneši atpakaļ |
|
args_tools.py
|
bd0ddf1cfe
feat: EETQ quantization (#408)
|
9 mēneši atpakaļ |
|
async_aphrodite.py
|
9aaeb5d349
add speculative config and arg for later
|
9 mēneši atpakaļ |
|
metrics.py
|
b1caee23a6
cache the p2p access check for memory saving
|
9 mēneši atpakaļ |
|
ray_tools.py
|
8c9cabf4c8
fix: display error in ray before deadlock (#378)
|
9 mēneši atpakaļ |
AlpinDale
a1f18f17e6
modify the cache engine and model runner/worker to support mamba states