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). @ ultravox

AlpinDale 1d3a1fec47 feat: add load/unload endpoints for soft-prompts (#694)		4 hónapja
..
rpc	7debd35ca2 fix: shut down ray dag workers cleanly (#692)	4 hónapja
__init__.py	07aa2a492f upstream: add option to specify tokenizer	1 éve
api_server.py	1d3a1fec47 feat: add load/unload endpoints for soft-prompts (#694)	4 hónapja
args.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
logits_processors.py	62111fab17 feat: allow serving encoder-decoder models in the API server (#664)	4 hónapja
protocol.py	81fa31bcaf feat: embeddings support for batched OAI endpoint (#676)	4 hónapja
run_batch.py	81fa31bcaf feat: embeddings support for batched OAI endpoint (#676)	4 hónapja
samplers.json	ac82b67f75 feat: naive context shift and various QoL changes (#289)	10 hónapja
serving_chat.py	3648170750 fix: gracefully handle missing chat template (#642)	4 hónapja
serving_completions.py	77c4fbd5c9 fix: better async request cancellation (#641)	4 hónapja
serving_embedding.py	81fa31bcaf feat: embeddings support for batched OAI endpoint (#676)	4 hónapja
serving_engine.py	1d3a1fec47 feat: add load/unload endpoints for soft-prompts (#694)	4 hónapja
serving_tokenization.py	3648170750 fix: gracefully handle missing chat template (#642)	4 hónapja