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). @ control-vectors

AlpinDale ba371fbbbd feat: AWQ marlin kernels (#603)		4 months ago
..
amd	251568470e initial nvidia fp8 e4m3 for kv cache	5 months ago
nvidia	3bdeb3e116 fix: clang formatting for all kernels (#558)	5 months ago
common.cu	c8f5424d72 add scale_ub inputs to fp8 dynamic per-token quant	4 months ago
fp8_marlin.cu	ba371fbbbd feat: AWQ marlin kernels (#603)	4 months ago