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). @ 8e7d214d2ddcd9e1e777ab941035aa63e7904efc

AlpinDale 8e7d214d2d Merge branch 'main' into lm_head_lora		2 weeks ago
..
__init__.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
bgmv_embed.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 month ago
bgmv_expand.py	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	1 month ago
bgmv_expand_slice.py	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	1 month ago
bgmv_sample.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 month ago
bgmv_shrink.py	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	1 month ago
sgmv_expand.py	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	1 month ago
sgmv_expand_slice.py	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	1 month ago
sgmv_shrink.py	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	1 month ago
utils.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 month ago