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). @ ee174ea4fd3bda4f206c74e0c3f53d978fb10475

AlpinDale 42d2ee0f43 chore: better error logging for unsupported lora weights		7 mēneši atpakaļ
..
__init__.py	2bd6c92f73 fix: lora inclusion in wheels	1 gadu atpakaļ
fully_sharded_layers.py	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	8 mēneši atpakaļ
layers.py	c975bba905 fix: sharded state loader with lora	7 mēneši atpakaļ
lora.py	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	8 mēneši atpakaļ
models.py	9e73559eba make use of batched rotary embedding kernels to support long context lora	8 mēneši atpakaļ
punica.py	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	8 mēneši atpakaļ
request.py	5b0c11d190 support pipeline parallel pynccl groups	8 mēneši atpakaļ
utils.py	42d2ee0f43 chore: better error logging for unsupported lora weights	7 mēneši atpakaļ
worker_manager.py	5fecc6b025 when was this deprecated?	7 mēneši atpakaļ