llama_inference 4bits error

[gjm441]

when I run the script：
CUDA_VISIBLE_DEVICES=0 python llama.py ${MODEL_DIR} c4 --wbits 4 --true-sequential --act-order --groupsize 128 --eval --save llama7b-4bit-128g.pt &>baseline.txt &

I got the same ppl as readme，But when infer with saved int4 weight：
CUDA_VISIBLE_DEVICES=0 python llama_inference.py decapoda-research/llama-7b-hf --wbits 4 --groupsize 128 --load llama7b-4bit-128g.pt --text "this is llama"
I get the error as follows：

---

Loading model ...
Found 3 unique KN Linear values.
Warming up autotune cache ...
0%| | 0/12 [00:00<?, ?it/s]/usr/bin/ld: cannot find -lcuda
collect2: error: ld returned 1 exit status
0%| | 0/12 [00:00<?, ?it/s]
Traceback (most recent call last):
File "", line 21, in matmul_248_kernel
KeyError: ('2-.-0-.-0-37ce7529e37ca1a0b8a47b63bc5fd4b0-d6252949da17ceb5f3a278a70250af13-3b85c7bef5f0a641282f3b73af50f599-2d732a2488b7ed996facc3e641ee56bf-3498c340fd4b6ee7805fd54b882a04f5-e1f133f98d04093da2078dfc51c36b72-b26258bf01f839199e39d64851821f26-d7c06e3b46e708006c15224aac7a1378-f585402118c8a136948ce0a49cfe122c', (torch.float16, torch.int32, torch.float16, torch.float16, torch.int32, torch.int32, 'i32', 'i32', 'i32', 'i32', 'i32', 'i32', 'i32', 'i32', 'i32', 'i32', 'i32', 'i32', 'i32'), (16, 256, 32, 8), (True, True, True, True, True, True, (False, True), (True, False), (True, False), (False, False), (False, False), (True, False), (False, True), (True, False), (False, True), (True, False), (False, True), (True, False), (True, False)))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/jingming.guo/Mars/GPTQ-for-LLaMa/llama.py", line 483, in
model = load_quant(args.model, args.load, args.wbits, args.groupsize)
File "/home/jingming.guo/Mars/GPTQ-for-LLaMa/llama.py", line 319, in load_quant
quant.autotune_warmup_linear(model, transpose=not (eval))
File "/home/jingming.guo/Mars/GPTQ-for-LLaMa/quant/quant_linear.py", line 419, in autotune_warmup_linear
matmul248(a, qweight, scales, qzeros, g_idx, bits, maxq)
File "/home/jingming.guo/Mars/GPTQ-for-LLaMa/quant/quant_linear.py", line 267, in matmul248
matmul_248_kernel[grid](input, qweight, output, scales, qzeros, g_idx, input.shape[0], qweight.shape[1], input.shape[1], bits, maxq, input.stride(0), input.stride(1), qweight.stride(0),
File "/home/jingming.guo/Mars/GPTQ-for-LLaMa/quant/custom_autotune.py", line 90, in run
timings = {config: self._bench(*args, config=config, **kwargs) for config in pruned_configs}
File "/home/jingming.guo/Mars/GPTQ-for-LLaMa/quant/custom_autotune.py", line 90, in
timings = {config: self._bench(*args, config=config, **kwargs) for config in pruned_configs}
File "/home/jingming.guo/Mars/GPTQ-for-LLaMa/quant/custom_autotune.py", line 72, in _bench
return triton.testing.do_bench(kernel_call, percentiles=(0.5, 0.2, 0.8), rep=40)
File "/home/anaconda3/envs/py39_ptq_jingming/lib/python3.9/site-packages/triton/testing.py", line 143, in do_bench
fn()
File "/home/jingming.guo/Mars/GPTQ-for-LLaMa/quant/custom_autotune.py", line 67, in kernel_call
self.fn.run(*args, num_warps=config.num_warps, num_stages=config.num_stages, **current)
File "", line 41, in matmul_248_kernel
File "/home/anaconda3/envs/py39_ptq_jingming/lib/python3.9/site-packages/triton/compiler.py", line 1588, in compile
so_path = make_stub(name, signature, constants)
File "/home/anaconda3/envs/py39_ptq_jingming/lib/python3.9/site-packages/triton/compiler.py", line 1477, in make_stub
so = _build(name, src_path, tmpdir)
File "/home/anaconda3/envs/py39_ptq_jingming/lib/python3.9/site-packages/triton/compiler.py", line 1392, in _build
ret = subprocess.check_call(cc_cmd)
File "/home/anaconda3/envs/py39_ptq_jingming/lib/python3.9/subprocess.py", line 373, in check_call
raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['/usr/bin/gcc', '/tmp/tmpaxcp747n/main.c', '-O3', '-I/usr/local/cuda/include', '-I/home/anaconda3/envs/py39_ptq_jingming/include/python3.9', '-I/tmp/tmpaxcp747n', '-shared', '-fPIC', '-lcuda', '-o', '/tmp/tmpaxcp747n/matmul_248_kernel.cpython-39-x86_64-linux-gnu.so', '-L/usr/share/man/man7']' returned non-zero exit status 1.