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 adb6982090 models: add support for IBM Granite (PowerLM) models (#978)		2 settimane fa
..
guided_decoding	e1eb7fbedc fix: SentencePieceTokenizer error when using mistral tokenizer mode (#943)	2 settimane fa
layers	201db10f02 models: add support for Phi3 MoE	2 settimane fa
model_loader	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	2 settimane fa
models	adb6982090 models: add support for IBM Granite (PowerLM) models (#978)	2 settimane fa
__init__.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	3 settimane fa
_custom_op.py	5d37ec1016 suppress tpu import warning (#696)	4 mesi fa
parameter.py	afc9a28aa0 chore: add AphroditeParameter support for FP8 quant (#902)	3 settimane fa
pooling_metadata.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesi fa
sampling_metadata.py	f0cc35befe sampler: pad dry sequence breakers tensor (#875)	1 mese fa
utils.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 mesi fa