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). @ lm_head_lora

AlpinDale eb1ffacf74 Spec Decoding: fix typical acceptance sampler with correct recovered tok IDs (#1106)		1 week geleden
..
__init__.py	c6c91edab7 ci: update & overhaul test units (#769)	2 maanden geleden
test_beam_search.py	9b317aa26a feat: finish up tests and workflows (#87)	1 jaar geleden
test_ignore_eos.py	c6c91edab7 ci: update & overhaul test units (#769)	2 maanden geleden
test_logits_processor.py	c6c91edab7 ci: update & overhaul test units (#769)	2 maanden geleden
test_logprobs.py	32a37e8107 tests: partially fix tensorizer and logprobs tests	2 maanden geleden
test_ranks.py	c6c91edab7 ci: update & overhaul test units (#769)	2 maanden geleden
test_rejection_sampling.py	a0f0160b79 spec decode: remove dead code from draft bonus tokens (#1101)	1 week geleden
test_sampler.py	1fac86c325 core: factor out common code in SequenceData (#1083)	3 weken geleden
test_seeded_generate.py	c6c91edab7 ci: update & overhaul test units (#769)	2 maanden geleden
test_typical_acceptance_sampler.py	eb1ffacf74 Spec Decoding: fix typical acceptance sampler with correct recovered tok IDs (#1106)	1 week geleden