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). @ get_last_latency_hack

AlpinDale 673621a3d2 xpu: refactor the model runner for tensor parallelism (#910)		1 mesiac pred
..
arctic_inference.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
cached_prefix_inference.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
embedding_inference.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
encoder_decoder_inference.py	62111fab17 feat: allow serving encoder-decoder models in the API server (#664)	4 mesiacov pred
gguf_inference.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
lora_aphrodite_engine.py	673621a3d2 xpu: refactor the model runner for tensor parallelism (#910)	1 mesiac pred
lora_async_aphrodite.py	673621a3d2 xpu: refactor the model runner for tensor parallelism (#910)	1 mesiac pred
mlpspeculator_inference.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
neuron_inference.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
offline_inference.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
ray_distributed_inference.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
soft_prompt_inference.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred