-
zhuwenwen authored
# Conflicts: # csrc/attention/attention_kernels.cu # csrc/attention/attention_utils.cuh # csrc/layernorm_kernels.cu # vllm/model_executor/layers/linear.py # vllm/model_executor/models/baichuan.py # vllm/model_executor/models/llama.py
1e77d04e