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). @ update_benchmarks

AlpinDale 60f7b828d5 feat: add skew sampling (#834)		1 mesiac pred
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	1 rok pred
block.py	7df7b8ca53 optimization: reduce end-to-end overhead from python obj allocation (#666)	4 mesiacov pred
config.py	2f61644f6e SPMD optimizations (#824)	2 mesiacov pred
connections.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
grammar.py	8a71788372 Add OLMoE (#772)	3 mesiacov pred
logger.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
logits_processor.py	8a71788372 Add OLMoE (#772)	3 mesiacov pred
outputs.py	0e558e9b2f fix: loading chameleon model with TP>1 (#695)	4 mesiacov pred
pooling_params.py	2f61644f6e SPMD optimizations (#824)	2 mesiacov pred
sampling_params.py	60f7b828d5 feat: add skew sampling (#834)	1 mesiac pred
sequence.py	48a8693aed feat: multi-step scheduling (#831)	2 mesiacov pred
test_utils.py	8a71788372 Add OLMoE (#772)	3 mesiacov pred
utils.py	0f1af04cf5 frontend: minor logging improvements (#787)	2 mesiacov pred