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). @ 6785d78d8224bde25e26085e25295d04788582ff

AlpinDale 6785d78d82 fix: do not expose EOS token in the API		vor 7 Monaten
..
attention	f40b809d3b allow using v2 block manager with sliding window	vor 7 Monaten
common	90ceab32ff refactor: consolidate prompt args to LLM engines	vor 7 Monaten
distributed	5b0c11d190 support pipeline parallel pynccl groups	vor 7 Monaten
endpoints	90ceab32ff refactor: consolidate prompt args to LLM engines	vor 7 Monaten
engine	6785d78d82 fix: do not expose EOS token in the API	vor 7 Monaten
executor	5b0c11d190 support pipeline parallel pynccl groups	vor 7 Monaten
kv_quant	e42a78381a feat: switch from pylint to ruff (#322)	vor 1 Jahr
lora	5b0c11d190 support pipeline parallel pynccl groups	vor 7 Monaten
modeling	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	vor 7 Monaten
processing	f40b809d3b allow using v2 block manager with sliding window	vor 7 Monaten
quantization	2649f3f14e aqlm works on pascal	vor 7 Monaten
spec_decode	344ddaac5a properly disable speculative decoding	vor 7 Monaten
task_handler	e4ea3da1ad fix: tensor parallel with embedding model	vor 7 Monaten
transformers_utils	60e74e92fd add rope_scaling arg	vor 7 Monaten
__init__.py	be8154a8a0 feat: proper embeddings API with e5-mistral-7b support	vor 7 Monaten
py.typed	1c988a48b2 fix logging and add py.typed	vor 1 Jahr