Was doing a demo task (replaced chatglm3_6b with chatglm3_6b_32k) and encountered AttributeError

[TriDefender]

I ran
(trt) C:\LLM\TensorRT-LLM\examples\chatglm>trtllm-build --checkpoint_dir trt_ckpt/chatglm3_6b_32k/fp16/1-gpu --gemm_plugin float16 --output_dir trt_engines/chatglm3_6b_32k/fp16/1-gpu
and got:

[TensorRT-LLM] TensorRT-LLM version: 0.14.0
[12/01/2024-13:36:10] [TRT-LLM] [I] Compute capability: (8, 9)
[12/01/2024-13:36:10] [TRT-LLM] [I] SM count: 34
[12/01/2024-13:36:10] [TRT-LLM] [I] SM clock: 3105 MHz
[12/01/2024-13:36:10] [TRT-LLM] [I] int4 TFLOPS: 216
[12/01/2024-13:36:10] [TRT-LLM] [I] int8 TFLOPS: 108
[12/01/2024-13:36:10] [TRT-LLM] [I] fp8 TFLOPS: 108
[12/01/2024-13:36:10] [TRT-LLM] [I] float16 TFLOPS: 54
[12/01/2024-13:36:10] [TRT-LLM] [I] bfloat16 TFLOPS: 54
[12/01/2024-13:36:10] [TRT-LLM] [I] float32 TFLOPS: 27
[12/01/2024-13:36:10] [TRT-LLM] [I] Total Memory: 15 GiB
[12/01/2024-13:36:10] [TRT-LLM] [I] Memory clock: 9001 MHz
[12/01/2024-13:36:10] [TRT-LLM] [I] Memory bus width: 128
[12/01/2024-13:36:10] [TRT-LLM] [I] Memory bandwidth: 288 GB/s
[12/01/2024-13:36:10] [TRT-LLM] [I] PCIe speed: 16000 Mbps
[12/01/2024-13:36:10] [TRT-LLM] [I] PCIe link width: 8
[12/01/2024-13:36:10] [TRT-LLM] [I] PCIe bandwidth: 16 GB/s
Traceback (most recent call last):
  File "C:\Users\18913\anaconda3\envs\trt\lib\runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "C:\Users\18913\anaconda3\envs\trt\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "C:\Users\18913\anaconda3\envs\trt\Scripts\trtllm-build.exe\__main__.py", line 7, in <module>
  File "C:\Users\18913\anaconda3\envs\trt\lib\site-packages\tensorrt_llm\commands\build.py", line 568, in main
    parallel_build(model_config, ckpt_dir, build_config, args.output_dir,
  File "C:\Users\18913\anaconda3\envs\trt\lib\site-packages\tensorrt_llm\commands\build.py", line 423, in parallel_build
    passed = build_and_save(rank, rank % workers, ckpt_dir,
  File "C:\Users\18913\anaconda3\envs\trt\lib\site-packages\tensorrt_llm\commands\build.py", line 390, in build_and_save
    engine = build_model(build_config,
  File "C:\Users\18913\anaconda3\envs\trt\lib\site-packages\tensorrt_llm\commands\build.py", line 335, in build_model
    assert not build_config.plugin_config.streamingllm or architecture == "LlamaForCausalLM", \
  File "C:\Users\18913\anaconda3\envs\trt\lib\site-packages\tensorrt_llm\plugin\plugin.py", line 95, in prop
    field_value = getattr(self, storage_name)
AttributeError: 'PluginConfig' object has no attribute '_streamingllm'. Did you mean: '_streamingllm'?
``
For more info this is a RTX 4060ti running on windows 11, tried with `--streamingllm ` and got same error, python is 3.10.0

(trt) C:\LLM\TensorRT-LLM\examples\chatglm>pip list
Package Version

---

absl-py 2.1.0
accelerate 1.1.1
aiohappyeyeballs 2.4.4
aiohttp 3.11.8
aiosignal 1.3.1
annotated-types 0.7.0
async-timeout 5.0.1
attrs 24.2.0
build 1.2.2.post1
certifi 2024.8.30
charset-normalizer 3.4.0
click 8.1.7
cloudpickle 3.1.0
colorama 0.4.6
colored 2.2.4
coloredlogs 15.0.1
cuda-python 12.5.0
datasets 2.14.7
diffusers 0.31.0
dill 0.3.7
evaluate 0.4.3
filelock 3.16.1
flatbuffers 24.3.25
frozenlist 1.5.0
fsspec 2023.10.0
h5py 3.10.0
huggingface-hub 0.26.3
humanfriendly 10.0
idna 3.10
importlib_metadata 8.5.0
janus 1.1.0
Jinja2 3.1.4
joblib 1.4.2
markdown-it-py 3.0.0
MarkupSafe 3.0.2
mdurl 0.1.2
mpmath 1.3.0
multidict 6.1.0
multiprocess 0.70.15
networkx 3.4.2
ninja 1.11.1.2
nltk 3.9.1
numpy 1.26.4
nvidia-cuda-runtime-cu12 12.6.77
nvidia-modelopt 0.17.0
onnx 1.17.0
onnxruntime 1.15.1
optimum 1.23.3
packaging 24.2
pandas 2.2.3
pillow 11.0.0
pip 24.2
polygraphy 0.49.9
propcache 0.2.0
protobuf 5.29.0
psutil 6.1.0
PuLP 2.9.0
pyarrow 18.1.0
pyarrow-hotfix 0.6
pydantic 2.10.2
pydantic_core 2.27.1
Pygments 2.18.0
pynvml 11.5.3
pyproject_hooks 1.2.0
pyreadline3 3.5.4
python-dateutil 2.9.0.post0
pytz 2024.2
pywin32 308
PyYAML 6.0.2
regex 2024.11.6
requests 2.32.3
rich 13.9.4
rouge_score 0.1.2
safetensors 0.4.5
scipy 1.14.1
sentencepiece 0.2.0
setuptools 75.1.0
six 1.16.0
StrEnum 0.4.15
sympy 1.13.3
tensorrt 10.4.0
tensorrt-cu12 10.4.0
tensorrt-cu12_bindings 10.4.0
tensorrt-cu12_libs 10.4.0
tensorrt-llm 0.14.0
tiktoken 0.8.0
tokenizers 0.19.1
tomli 2.2.1
torch 2.4.1+cu124
torchprofile 0.0.4
torchvision 0.19.1+cu124
tqdm 4.67.1
transformers 4.43.0
typing_extensions 4.12.2
tzdata 2024.2
urllib3 2.2.3
wheel 0.44.0
xxhash 3.5.0
yarl 1.18.0
zipp 3.21.0

[TriDefender]

PS C:\Users\18913> nvidia-smi
Sun Dec  1 13:42:33 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 566.14                 Driver Version: 566.14         CUDA Version: 12.7     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                  Driver-Model | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA GeForce RTX 4060 Ti   WDDM  |   00000000:01:00.0  On |                  N/A |
|  0%   49C    P8              4W /  176W |     974MiB /  16380MiB |      3%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+