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		2 долоо хоног өмнө
..
__init__.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 сар өмнө
bgmv_embed.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 сар өмнө
bgmv_expand.py	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	1 сар өмнө
bgmv_expand_slice.py	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	1 сар өмнө
bgmv_sample.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 сар өмнө
bgmv_shrink.py	bf4a4d8516 fix: do not register punica with torch if using older torch (#948)	1 сар өмнө
sgmv_expand.py	69cf654901 LoRA: add assertions for SGMV kernels to avoid incorrect results (#1104)	2 долоо хоног өмнө
sgmv_expand_slice.py	69cf654901 LoRA: add assertions for SGMV kernels to avoid incorrect results (#1104)	2 долоо хоног өмнө
sgmv_shrink.py	69cf654901 LoRA: add assertions for SGMV kernels to avoid incorrect results (#1104)	2 долоо хоног өмнө
utils.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	1 сар өмнө