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). @ fully-sharded-lora-fix

AlpinDale ab533e0e60 spec decode: fix logprobs when using speculative decoding (#904)		1 mese fa
..
e2e	ab533e0e60 spec decode: fix logprobs when using speculative decoding (#904)	1 mese fa
__init__.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_batch_expansion.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_dynamic_spec_decode.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_metrics.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_multi_step_worker.py	132aa2abe4 spec decode: add support for EAGLE (#899)	1 mese fa
test_ngram_worker.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_spec_decode_worker.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
test_utils.py	c6c91edab7 ci: update & overhaul test units (#769)	2 mesi fa
utils.py	2f61644f6e SPMD optimizations (#824)	2 mesi fa