david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ rejection_sampling_kernels

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