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). @ 058e629f8e26c83b4bc839fac444c66734975ba5

AlpinDale f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)		1 rok pred
..
README	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	1 rok pred
attention_dtypes.h	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	1 rok pred
attention_kernels.cu	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	1 rok pred
cache.h	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	1 rok pred
cache_kernels.cu	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	1 rok pred
dispatch_utils.h	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	1 rok pred
dtype_float32.cuh	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	1 rok pred
dtype_int8.cuh	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	1 rok pred
ops.h	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	1 rok pred

		
				README
			
				Backup of attention and cache kernels from INT8 KV Cache. Will be restored soon.