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). @ lm_head_lora

AlpinDale 8e7d214d2d Merge branch 'main' into lm_head_lora		2 weken geleden
..
ops	8e7d214d2d Merge branch 'main' into lm_head_lora	2 weken geleden
__init__.py	2bd6c92f73 fix: lora inclusion in wheels	11 maanden geleden
fully_sharded_layers.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 maanden geleden
layers.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 maand geleden
lora.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 maand geleden
models.py	8e7d214d2d Merge branch 'main' into lm_head_lora	2 weken geleden
punica.py	8e7d214d2d Merge branch 'main' into lm_head_lora	2 weken geleden
request.py	6212072245 api: support LoRA lineage and base model metadata management (#1072)	3 weken geleden
utils.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 maand geleden
worker_manager.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 maand geleden