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). @ dynatempagain

AlpinDale 48f7216c49 add to procotol		5 mēneši atpakaļ
..
rpc	77c4fbd5c9 fix: better async request cancellation (#641)	5 mēneši atpakaļ
__init__.py	07aa2a492f upstream: add option to specify tokenizer	1 gadu atpakaļ
api_server.py	59264d32e9 fix: hardcoded float16 in embedding mode check (#645)	5 mēneši atpakaļ
args.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 mēneši atpakaļ
logits_processors.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 mēneši atpakaļ
protocol.py	48f7216c49 add to procotol	5 mēneši atpakaļ
run_batch.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 mēneši atpakaļ
samplers.json	ac82b67f75 feat: naive context shift and various QoL changes (#289)	11 mēneši atpakaļ
serving_chat.py	3648170750 fix: gracefully handle missing chat template (#642)	5 mēneši atpakaļ
serving_completions.py	77c4fbd5c9 fix: better async request cancellation (#641)	5 mēneši atpakaļ
serving_embedding.py	77c4fbd5c9 fix: better async request cancellation (#641)	5 mēneši atpakaļ
serving_engine.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 mēneši atpakaļ
serving_tokenization.py	3648170750 fix: gracefully handle missing chat template (#642)	5 mēneši atpakaļ