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). @ feat/function-calling

AlpinDale 1c46fa31ad feat: add quadratic sampling (#233)		11 månader sedan
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	1 år sedan
block.py	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	11 månader sedan
config.py	c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228)	11 månader sedan
grammar.py	0adab894fe feat: grammar support (#206)	11 månader sedan
logger.py	8834ecf9de chore: clean up refactor endpoints (#98)	1 år sedan
logits_processor.py	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	11 månader sedan
outputs.py	c0aac15421 feat: S-LoRA support (#222)	11 månader sedan
prefix.py	c0aac15421 feat: S-LoRA support (#222)	11 månader sedan
sampling_params.py	1c46fa31ad feat: add quadratic sampling (#233)	11 månader sedan
sequence.py	c0aac15421 feat: S-LoRA support (#222)	11 månader sedan
test_utils.py	641bb0f6e9 feat: add custom allreduce kernels (#224)	11 månader sedan
utils.py	31c95011a6 feat: FP8 E5M2 KV Cache (#226)	11 månader sedan