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). @ 28866137ea478ce53b0f72be28fa05a13836323b

AlpinDale 28866137ea feat: add swiglu activation		il y a 1 an
..
attention	05d0a7e763 feat: adapt the attention kernels	il y a 1 an
activation.cpp	28866137ea feat: add swiglu activation	il y a 1 an
activation_kernels.cu	28866137ea feat: add swiglu activation	il y a 1 an
attention.cpp	d40a8d6bb0 chore: bind single_query_cached_kv_attention to python	il y a 1 an
cache.cpp	a409431c40 feat: draft for cuda kernels	il y a 1 an
cache_kernels.cu	a409431c40 feat: draft for cuda kernels	il y a 1 an