xiaonans a98573990b Accelerate llama (#219) ... * [feature] add cudagraph support * modify code to pass the cuda_all_reduce test * modify rope op * support rmsnorm * add fp16 support to silu cuda op * fix bugs in rmsnorm op * uncomment simplify in onnx.py --------- Co-authored-by: Haojie Wang <haojie0429@gmail.com>		2024-04-01 08:46:05 +08:00
..
bang	fix mlu some kernel registration & gather op (#210)	2024-02-01 15:02:02 +08:00
core	Accelerate llama (#219)	2024-04-01 08:46:05 +08:00
cuda	Accelerate llama (#219)	2024-04-01 08:46:05 +08:00
ffi	Add TVM codegen for MemboundOp (#35)	2022-09-22 18:06:45 +08:00
intelcpu	Cpu backend2 (#77)	2023-04-17 12:15:23 +08:00
kunlun	XCCL support (#171)	2024-02-29 11:48:35 +08:00
nnet	test: 支持编译 einnet 单元测试，但不是所有测试都能通过 (#174)	2023-11-03 13:21:49 +08:00
operators	Accelerate llama (#219)	2024-04-01 08:46:05 +08:00
utils	XCCL support (#171)	2024-02-29 11:48:35 +08:00
test.h	Add python interface for CUDA operator evaluation (#42)	2022-09-27 10:41:12 +08:00