| .. |
|
output_processor
|
09dab16f82
core: improve async postproc + multi-step performance (#983)
|
vor 2 Monaten |
|
__init__.py
|
04b53d2db5
chore: add initializer files
|
vor 1 Jahr |
|
aphrodite_engine.py
|
05be6085ec
core: factor out input preprocessing into a separate class (#1039)
|
vor 2 Monaten |
|
args_tools.py
|
271879a4a5
fix: disable chunked prefill and prefix caching for multimodal models (#1037)
|
vor 2 Monaten |
|
async_aphrodite.py
|
05be6085ec
core: factor out input preprocessing into a separate class (#1039)
|
vor 2 Monaten |
|
async_timeout.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 6 Monaten |
|
metrics.py
|
3d83e64f8e
feat: add metrics for prefix cache hit rate (#829)
|
vor 3 Monaten |
|
metrics_types.py
|
3d83e64f8e
feat: add metrics for prefix cache hit rate (#829)
|
vor 3 Monaten |
|
protocol.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
vor 2 Monaten |
AlpinDale
05be6085ec
core: factor out input preprocessing into a separate class (#1039)