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).

AlpinDale 3bb0f07461 chore: rename `task_handler` to `worker` (#985)		před 2 týdny
..
README	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	před 9 měsíci
attention_dtypes.h	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	před 9 měsíci
attention_kernels.cu	3bb0f07461 chore: rename `task_handler` to `worker` (#985)	před 2 týdny
cache.h	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	před 9 měsíci
cache_kernels.cu	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	před 9 měsíci
dispatch_utils.h	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	před 9 měsíci
dtype_float32.cuh	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	před 9 měsíci
dtype_int8.cuh	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	před 9 měsíci
ops.h	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	před 9 měsíci

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