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). @ fc5ef786b0c63ef9fa00e95dd94c3f592be18d20

AlpinDale fc5ef786b0 Merge branch 'main' into lm_head_lora		1 tydzień temu
..
ops	fc5ef786b0 Merge branch 'main' into lm_head_lora	1 tydzień temu
__init__.py	2bd6c92f73 fix: lora inclusion in wheels	1 rok temu
fully_sharded_layers.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 miesięcy temu
layers.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 miesiąc temu
lora.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 miesiąc temu
models.py	8e7d214d2d Merge branch 'main' into lm_head_lora	1 miesiąc temu
punica.py	fc5ef786b0 Merge branch 'main' into lm_head_lora	1 tydzień temu
request.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	1 miesiąc temu
utils.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 miesiąc temu
worker_manager.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 miesiąc temu