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

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