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 80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters		3 weeks ago
..
ops	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	3 weeks ago
__init__.py	2bd6c92f73 fix: lora inclusion in wheels	11 months ago
fully_sharded_layers.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
layers.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	3 weeks ago
lora.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	3 weeks ago
models.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	3 weeks ago
punica.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	3 weeks ago
request.py	2f61644f6e SPMD optimizations (#824)	1 month ago
utils.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	3 weeks ago
worker_manager.py	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	3 weeks ago