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 f7f3fed265 feat: add async postprocessor (#925)		2 weeks ago
..
block	9c9b2dd843 core: improve warmup times for prefix caching in block manager v2 (#920)	2 weeks ago
__init__.py	c6c91edab7 ci: update & overhaul test units (#769)	1 month ago
test_block_manager.py	abfd4465ca feat: add support for chunked prefill + prefix caching (#871)	1 month ago
test_chunked_prefill_scheduler.py	f7f3fed265 feat: add async postprocessor (#925)	2 weeks ago
test_scheduler.py	c6c91edab7 ci: update & overhaul test units (#769)	1 month ago
test_scheduler_encoder_decoder.py	c6c91edab7 ci: update & overhaul test units (#769)	1 month ago
test_serialization.py	2f61644f6e SPMD optimizations (#824)	1 month ago
utils.py	f7f3fed265 feat: add async postprocessor (#925)	2 weeks ago