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). @ deepseek_v3

AlpinDale 411ac4f405 vlm: add support for Qwen2-VL model (#1015)		4 settimane fa
..
configs	411ac4f405 vlm: add support for Qwen2-VL model (#1015)	4 settimane fa
tokenizer_group	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesi fa
tokenizers	f644e10449 vlm: enable multimodal inputs for the LLM class (#992)	1 mese fa
__init__.py	267c73c5d3 chore: minor tokenizer tweaks	1 anno fa
config.py	411ac4f405 vlm: add support for Qwen2-VL model (#1015)	4 settimane fa
detokenizer.py	4648f16c84 chore: fix return statement in Detokenizer class (#727)	4 mesi fa
image_processor.py	be59e30139 vlm: add support for video modality + llava next video (#1014)	4 settimane fa
processor.py	411ac4f405 vlm: add support for Qwen2-VL model (#1015)	4 settimane fa
tokenizer.py	d5033e12fd feat: implement mistral tokenizer mode (#711)	4 mesi fa
utils.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesi fa