CUDA kernels from PEFT v0.11.0 breaks C++ compilation about peft HOT 4 CLOSED

def install_llama_cpp_blocking(use_cuda = True):
    import subprocess
    import os
    import psutil
    # https://github.com/ggerganov/llama.cpp/issues/7062
    # Weirdly GPU conversion for GGUF breaks??
    # use_cuda = "LLAMA_CUDA=1" if use_cuda else ""

    commands = [
        "git clone --recursive https://github.com/ggerganov/llama.cpp",
        "make clean -C llama.cpp",
        # https://github.com/ggerganov/llama.cpp/issues/7062
        # Weirdly GPU conversion for GGUF breaks??
        # f"{use_cuda} make all -j{psutil.cpu_count()*2} -C llama.cpp",
        f"make all -j{psutil.cpu_count()*2} -C llama.cpp",
        "pip install gguf protobuf",
    ]
    # if os.path.exists("llama.cpp"): return

    for command in commands:
        with subprocess.Popen(command, shell = True, stdout = subprocess.PIPE, stderr = subprocess.STDOUT, bufsize = 1) as sp:
            for line in sp.stdout:
                line = line.decode("utf-8", errors = "replace")
                if "undefined reference" in line:
                    raise RuntimeError("Failed compiling llama.cpp")
                # print(line, flush = True, end = "")
        pass
    pass
pass

import os
import subprocess
from peft import PeftModelForCausalLM

os.chdir("/tmp/")

commands = [
    "git clone --recursive https://github.com/ggerganov/llama.cpp",
    "make clean -C llama.cpp",
    "make all -j4 -C llama.cpp",
    "echo $?",
]

for command in commands:
    with subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, bufsize=1) as sp:
        for line in sp.stdout:
            line = line.decode("utf-8", errors = "replace")
            print(line, end = "")
            if "undefined reference" in line:
                raise RuntimeError("Failed compiling llama.cpp")
    print(f"-------------- finished: {command} --------------")
print("done")