yuehuayingxueluo 87079cffe8 [Inference]Support FP16/BF16 Flash Attention 2 And Add high_precision Flag To Rotary Embedding (#5461) ... * Support FP16/BF16 Flash Attention 2 * fix bugs in test_kv_cache_memcpy.py * add context_kv_cache_memcpy_kernel.cu * rm typename MT * add tail process * add high_precision * add high_precision to config.py * rm unused code * change the comment for the high_precision parameter * update test_rotary_embdding_unpad.py * fix vector_copy_utils.h * add comment for self.high_precision when using float32		2024-03-25 13:40:34 +08:00
..
layers	[Inference]Fused the gate and up proj in mlp，and optimized the autograd process. (#5365)	2024-02-06 19:38:25 +08:00
models	[Inference]Support FP16/BF16 Flash Attention 2 And Add high_precision Flag To Rotary Embedding (#5461)	2024-03-25 13:40:34 +08:00
policy	feat rmsnorm cuda kernel and add unittest, benchmark script (#5417)	2024-03-08 16:21:12 +08:00
__init__.py	[doc] updated inference readme (#5343)	2024-02-02 14:31:10 +08:00