AlpinDale d4e78a428b fix: crash when cancelling a request with multi-step (#977) vor 1 Monat
..
output_processor d4e78a428b fix: crash when cancelling a request with multi-step (#977) vor 1 Monat
__init__.py 04b53d2db5 chore: add initializer files vor 1 Jahr
aphrodite_engine.py b3f6eeb1d2 vlm: increase the default `max_num_batched_tokens` for multimodal models (#973) vor 1 Monat
args_tools.py 510ae5b949 core: fix chunked prefill not being enabled by default for long contexts (#974) vor 1 Monat
async_aphrodite.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) vor 1 Monat
async_timeout.py f1d0b77c92 [0.6.0] Release Candidate (#481) vor 4 Monaten
metrics.py 3d83e64f8e feat: add metrics for prefix cache hit rate (#829) vor 2 Monaten
metrics_types.py 3d83e64f8e feat: add metrics for prefix cache hit rate (#829) vor 2 Monaten
protocol.py 0dfa6b60ec core: support logprobs with multi-step scheduling (#963) vor 1 Monat