• zhuwenwen's avatar
    Merge branch 'v0.5.0-dtk24.04.1' into v0.5.2-dtk24.04.1 · 1e77d04e
    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
torch_bindings.cpp 12.3 KB