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).

AlpinDale 1fac86c325 core: factor out common code in SequenceData (#1083)		vor 8 Stunden
..
e2e	0859dc3bc0 tests: refactor speculative decoding tests to remove the async engine (#1021)	vor 1 Woche
__init__.py	c6c91edab7 ci: update & overhaul test units (#769)	vor 1 Monat
test_batch_expansion.py	c6c91edab7 ci: update & overhaul test units (#769)	vor 1 Monat
test_dynamic_spec_decode.py	c6c91edab7 ci: update & overhaul test units (#769)	vor 1 Monat
test_metrics.py	c6c91edab7 ci: update & overhaul test units (#769)	vor 1 Monat
test_multi_step_worker.py	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	vor 2 Wochen
test_ngram_worker.py	c6c91edab7 ci: update & overhaul test units (#769)	vor 1 Monat
test_spec_decode_worker.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	vor 2 Wochen
test_utils.py	564d197687 spec decode: match the original rank computation impl for spec decoding (#954)	vor 2 Wochen
utils.py	1fac86c325 core: factor out common code in SequenceData (#1083)	vor 8 Stunden