Compile issue on Linux

[jasonmhead]

Switched over to Linux, installed ninja, and have a compile issue perhaps.
Suggestions?

python chat.py


ChatRWKV v2 https://github.com/BlinkDL/ChatRWKV

English - cuda fp16 - /media/main/C/Users/Jason/Documents/machine_learning/language_ML/ChatRWKV/v2/prompt/default/English-2.py
Using /home/main/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
Detected CUDA files, patching ldflags
Emitting ninja build file /home/main/.cache/torch_extensions/py39_cu117/wkv_cuda/build.ninja...
Building extension module wkv_cuda...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/1] c++ wrapper.o operators.cuda.o -shared -L/home/main/miniconda3/envs/gptj/lib/python3.9/site-packages/torch/lib -lc10 -lc10_cuda -ltorch_cpu -ltorch_cuda_cu -ltorch_cuda_cpp -ltorch -ltorch_python -L/home/main/miniconda3/envs/gptj/lib64 -lcudart -o wkv_cuda.so
FAILED: wkv_cuda.so 
c++ wrapper.o operators.cuda.o -shared -L/home/main/miniconda3/envs/gptj/lib/python3.9/site-packages/torch/lib -lc10 -lc10_cuda -ltorch_cpu -ltorch_cuda_cu -ltorch_cuda_cpp -ltorch -ltorch_python -L/home/main/miniconda3/envs/gptj/lib64 -lcudart -o wkv_cuda.so
/usr/bin/ld: cannot find -lcudart: No such file or directory
collect2: error: ld returned 1 exit status
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
  File "/home/main/miniconda3/envs/gptj/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1900, in _run_ninja_build
    subprocess.run(
  File "/home/main/miniconda3/envs/gptj/lib/python3.9/subprocess.py", line 528, in run
    raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/media/main/C/Users/Jason/Documents/machine_learning/language_ML/ChatRWKV/v2/chat.py", line 105, in <module>
    from rwkv.model import RWKV
  File "/media/main/C/Users/Jason/Documents/machine_learning/language_ML/ChatRWKV/v2/../rwkv_pip_package/src/rwkv/model.py", line 29, in <module>
    load(
  File "/home/main/miniconda3/envs/gptj/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1284, in load
    return _jit_compile(
  File "/home/main/miniconda3/envs/gptj/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1508, in _jit_compile
    _write_ninja_file_and_build_library(
  File "/home/main/miniconda3/envs/gptj/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1623, in _write_ninja_file_and_build_library
    _run_ninja_build(
  File "/home/main/miniconda3/envs/gptj/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1916, in _run_ninja_build
    raise RuntimeError(message) from e
RuntimeError: Error building extension 'wkv_cuda'

[BlinkDL]

Please read https://github.com/BlinkDL/ChatRWKV README

Note RWKV_CUDA_ON will build a CUDA kernel ("pip install ninja" first).

How to build in Linux: set these and run v2/chat.py

export PATH=/usr/local/cuda/bin:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda/lib64:$LD_LIBRARY_PATH