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/t5-support

AlpinDale 72659e5cad separate prompt and genned tokens for enc-dec		10 miesięcy temu
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	1 rok temu
block.py	ac82b67f75 feat: naive context shift and various QoL changes (#289)	10 miesięcy temu
config.py	c41462cfcd feat: exllamav2 quantization (#305)	10 miesięcy temu
gguf.py	e42a78381a feat: switch from pylint to ruff (#322)	10 miesięcy temu
grammar.py	0527131e93 fix: grammar logits processor (#268)	11 miesięcy temu
logger.py	e42a78381a feat: switch from pylint to ruff (#322)	10 miesięcy temu
logits_processor.py	3df36ee07d fix: logit bias logitproc (#278)	10 miesięcy temu
outputs.py	e42a78381a feat: switch from pylint to ruff (#322)	10 miesięcy temu
sampling_params.py	e42a78381a feat: switch from pylint to ruff (#322)	10 miesięcy temu
sequence.py	72659e5cad separate prompt and genned tokens for enc-dec	10 miesięcy temu
test_utils.py	641bb0f6e9 feat: add custom allreduce kernels (#224)	1 rok temu
utils.py	e53842bd5d fix: cuda home detection for fp8 kv cache	10 miesięcy temu