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). @ 82128ec8438f369e2926c9e685653ab4f8ddd288

AlpinDale 16b587c104 fix: hidden states handling in batch expansion for spec decoding (#839)		hai 1 mes
..
__init__.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
conftest.py	16b587c104 fix: hidden states handling in batch expansion for spec decoding (#839)	hai 1 mes
test_compatibility.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_integration.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_integration_dist_tp2.py	2f61644f6e SPMD optimizations (#824)	hai 1 mes
test_integration_dist_tp4.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_logprobs.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_medusa_correctness.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_mlp_correctness.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_multistep_correctness.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_ngram_correctness.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes
test_seed.py	c6c91edab7 ci: update & overhaul test units (#769)	hai 1 mes