• zhuwenwen's avatar
    Merge branch 'v0.6.2-eval' into v0.6.2-dev · 3f42b83d
    zhuwenwen authored
    # Conflicts:
    #	csrc/attention/static_switch_tc.h
    #	vllm/model_executor/layers/vocab_parallel_embedding.py
    #	vllm/model_executor/model_loader/utils.py
    #	vllm/model_executor/models/llama.py
    3f42b83d
llama.py 28.9 KB