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). @ afb8cfe9457e380b4804601eb8ad805a28f3204d

AlpinDale afb8cfe945 feat: add most of the EETQ kernels, prune later		8 месяцев назад
..
cutlass_extensions	afb8cfe945 feat: add most of the EETQ kernels, prune later	8 месяцев назад
cutlass_kernels	afb8cfe945 feat: add most of the EETQ kernels, prune later	8 месяцев назад
utils	afb8cfe945 feat: add most of the EETQ kernels, prune later	8 месяцев назад
weightOnlyBatchedGemv	afb8cfe945 feat: add most of the EETQ kernels, prune later	8 месяцев назад
CMakeLists.txt	afb8cfe945 feat: add most of the EETQ kernels, prune later	8 месяцев назад
LICENSE	afb8cfe945 feat: add most of the EETQ kernels, prune later	8 месяцев назад
README	afb8cfe945 feat: add most of the EETQ kernels, prune later	8 месяцев назад
README.md	afb8cfe945 feat: add most of the EETQ kernels, prune later	8 месяцев назад
eetpy.cpp	afb8cfe945 feat: add most of the EETQ kernels, prune later	8 месяцев назад

		
				README
			
				These kernels are adapted from https://github.com/NetEase-FuXi/EETQ/tree/main/csrc