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). @ revert_871

AlpinDale 0bf916eabd Revert "feat: add support for chunked prefill + prefix caching (#871)"		3 settimane fa
..
block	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	1 mese fa
__init__.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_block_manager.py	0bf916eabd Revert "feat: add support for chunked prefill + prefix caching (#871)"	3 settimane fa
test_chunked_prefill_scheduler.py	0bf916eabd Revert "feat: add support for chunked prefill + prefix caching (#871)"	3 settimane fa
test_scheduler.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_scheduler_encoder_decoder.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa
test_serialization.py	2f61644f6e SPMD optimizations (#824)	1 mese fa
utils.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mese fa