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 d9d287a288 rocm: enable multi-step scheduling for rocm (#1071)		před 5 dny
..
backends	d9d287a288 rocm: enable multi-step scheduling for rocm (#1071)	před 5 dny
ops	e200775863 feat: enable using fp8 kv and prefix caching with chunked prefill (#668)	před 4 měsíci
__init__.py	1405051912 attention: add `AttentionState` abstraction (#863)	před 1 měsícem
layer.py	bf88c8567e feat: mamba model support (#674)	před 4 měsíci
selector.py	4ddc14d653 core: use flashinfer for FP8 KV when available (#944)	před 2 týdny