You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

yuehuayingxueluo 934e31afb2 The writing style of tail processing and the logic related to macro definitions have been optimized. (#5519)		8 months ago
..
benchmark_ops	[Inference/kernel]Add Fused Rotary Embedding and KVCache Memcopy CUDA Kernel (#5418)	9 months ago
benchmark_llama.py	[Inference]Support FP16/BF16 Flash Attention 2 And Add high_precision Flag To Rotary Embedding (#5461)	8 months ago
build_smoothquant_weight.py	[inference] refactor examples and fix schedule (#5077)	1 year ago
run_benchmark.sh	The writing style of tail processing and the logic related to macro definitions have been optimized. (#5519)	8 months ago
run_llama_inference.py	[npu] change device to accelerator api (#5239)	11 months ago