Task 38487501

Name test_2-SFARR_TEST_LLM_WINDOWS_101_7-0-1-RND9798_1
Workunit 31482406
Created 24 Apr 2025, 14:54:27 UTC
Sent 24 Apr 2025, 14:55:37 UTC
Report deadline 29 Apr 2025, 14:55:37 UTC
Received 24 Apr 2025, 15:02:17 UTC
Server state Over
Outcome Computation error
Client state Compute error
Exit status 195 (0x000000C3) EXIT_CHILD_FAILED
Computer ID 611060
Run time 4 min 12 sec
CPU time 1 min 11 sec
Validate state Invalid
Credit 0.00
Device peak FLOPS 82,576.36 GFLOPS
Application version LLM: LLMs for chemistry v1.01 (cuda124L)
windows_x86_64
Peak working set size 816.38 MB
Peak swap size 2.51 GB
Peak disk usage 6.15 GB

Stderr output

<core_client_version>8.0.2</core_client_version>
<![CDATA[
<message>
The operating system cannot run (null).
 (0xc3) - exit code 195 (0xc3)</message>
<stderr_txt>
07:58:09 (40564): wrapper (7.9.26016): starting
07:58:09 (40564): wrapper: running Library/usr/bin/tar.exe (xjvf input.tar.bz2)
conf.yaml
main_generation-0.1.0-py3-none-any.whl
run.bat
run.sh
tasks.json
07:58:10 (40564): Library/usr/bin/tar.exe exited; CPU time 0.000000
07:58:10 (40564): wrapper: running C:/Windows/system32/cmd.exe (/c call Scripts\activate.bat && Scripts\conda-unpack.exe && run.bat)
[W424 08:00:16.000000000 socket.cpp:759] [c10d] The client socket has failed to connect to [ct-office]:56877 (system error: 10049 - The requested address is not valid in its context.).
[rank0]: Traceback (most recent call last):
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\layers\quantization\bitsandbytes.py", line 158, in __init__
[rank0]:     import bitsandbytes
[rank0]: ModuleNotFoundError: No module named 'bitsandbytes'

[rank0]: The above exception was the direct cause of the following exception:

[rank0]: Traceback (most recent call last):
[rank0]:   File "wheel_contents/aiengine/main_generation.py", line 86, in <module>
[rank0]:   File "wheel_contents/aiengine/model.py", line 36, in __init__
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\utils.py", line 1096, in inner
[rank0]:     return fn(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\entrypoints\llm.py", line 243, in __init__
[rank0]:     self.llm_engine = LLMEngine.from_engine_args(
[rank0]:                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\engine\llm_engine.py", line 521, in from_engine_args
[rank0]:     return engine_cls.from_vllm_config(
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\engine\llm_engine.py", line 497, in from_vllm_config
[rank0]:     return cls(
[rank0]:            ^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\engine\llm_engine.py", line 281, in __init__
[rank0]:     self.model_executor = executor_class(vllm_config=vllm_config, )
[rank0]:                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\executor\executor_base.py", line 52, in __init__
[rank0]:     self._init_executor()
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\executor\uniproc_executor.py", line 47, in _init_executor
[rank0]:     self.collective_rpc("load_model")
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\executor\uniproc_executor.py", line 56, in collective_rpc
[rank0]:     answer = run_method(self.driver_worker, method, args, kwargs)
[rank0]:              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\utils.py", line 2359, in run_method
[rank0]:     return func(*args, **kwargs)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\worker\worker.py", line 184, in load_model
[rank0]:     self.model_runner.load_model()
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\worker\model_runner.py", line 1113, in load_model
[rank0]:     self.model = get_model(vllm_config=self.vllm_config)
[rank0]:                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\model_loader\__init__.py", line 14, in get_model
[rank0]:     return loader.load_model(vllm_config=vllm_config)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\model_loader\loader.py", line 1278, in load_model
[rank0]:     model = _initialize_model(vllm_config=vllm_config)
[rank0]:             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\model_loader\loader.py", line 127, in _initialize_model
[rank0]:     return model_class(vllm_config=vllm_config, prefix=prefix)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\models\qwen2.py", line 431, in __init__
[rank0]:     self.model = Qwen2Model(vllm_config=vllm_config,
[rank0]:                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\compilation\decorators.py", line 151, in __init__
[rank0]:     old_init(self, vllm_config=vllm_config, prefix=prefix, **kwargs)
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\models\qwen2.py", line 300, in __init__
[rank0]:     self.start_layer, self.end_layer, self.layers = make_layers(
[rank0]:                                                     ^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\models\utils.py", line 610, in make_layers
[rank0]:     maybe_offload_to_cpu(layer_fn(prefix=f"{prefix}.{idx}"))
[rank0]:                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\models\qwen2.py", line 302, in <lambda>
[rank0]:     lambda prefix: Qwen2DecoderLayer(config=config,
[rank0]:                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\models\qwen2.py", line 206, in __init__
[rank0]:     self.self_attn = Qwen2Attention(
[rank0]:                      ^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\models\qwen2.py", line 136, in __init__
[rank0]:     self.qkv_proj = QKVParallelLinear(
[rank0]:                     ^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\layers\linear.py", line 833, in __init__
[rank0]:     super().__init__(input_size=input_size,
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\layers\linear.py", line 384, in __init__
[rank0]:     super().__init__(input_size,
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\layers\linear.py", line 231, in __init__
[rank0]:     self.quant_method = quant_config.get_quant_method(self,
[rank0]:                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\layers\quantization\bitsandbytes.py", line 128, in get_quant_method
[rank0]:     return BitsAndBytesLinearMethod(self)
[rank0]:            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]:   File "C:\ProgramData\BOINC\slots\32\Lib\site-packages\vllm\model_executor\layers\quantization\bitsandbytes.py", line 163, in __init__
[rank0]:     raise ImportError("Please install bitsandbytes>=0.45.3 via "
[rank0]: ImportError: Please install bitsandbytes>=0.45.3 via `pip install bitsandbytes>=0.45.3` to use bitsandbytes quantizer.
08:00:20 (40564): C:/Windows/system32/cmd.exe exited; CPU time 71.781250
08:00:20 (40564): app exit status: 0x16
08:00:20 (40564): called boinc_finish(195)
0 bytes in 0 Free Blocks.
460 bytes in 8 Normal Blocks.
1144 bytes in 1 CRT Blocks.
0 bytes in 0 Ignore Blocks.
0 bytes in 0 Client Blocks.
Largest number used: 0 bytes.
Total allocations: 2255093 bytes.
Dumping objects ->
{1601476} normal block at 0x000001D74F1D5970, 48 bytes long.
 Data: <PATH=C:\ProgramD> 50 41 54 48 3D 43 3A 5C 50 72 6F 67 72 61 6D 44 
{1601465} normal block at 0x000001D74F1D5900, 48 bytes long.
 Data: <HOME=C:\ProgramD> 48 4F 4D 45 3D 43 3A 5C 50 72 6F 67 72 61 6D 44 
{1601454} normal block at 0x000001D74F1D5890, 48 bytes long.
 Data: <TMP=C:\ProgramDa> 54 4D 50 3D 43 3A 5C 50 72 6F 67 72 61 6D 44 61 
{1601443} normal block at 0x000001D74F1D57B0, 48 bytes long.
 Data: <TEMP=C:\ProgramD> 54 45 4D 50 3D 43 3A 5C 50 72 6F 67 72 61 6D 44 
{1601432} normal block at 0x000001D74F1D56D0, 48 bytes long.
 Data: <TMPDIR=C:\Progra> 54 4D 50 44 49 52 3D 43 3A 5C 50 72 6F 67 72 61 
{1601401} normal block at 0x000001D750F5C680, 64 bytes long.
 Data: <PATH=C:\ProgramD> 50 41 54 48 3D 43 3A 5C 50 72 6F 67 72 61 6D 44 
{1601390} normal block at 0x000001D750DA15A0, 102 bytes long.
 Data: <<project_prefere> 3C 70 72 6F 6A 65 63 74 5F 70 72 65 66 65 72 65 
..\api\boinc_api.cpp(309) : {1601387} normal block at 0x000001D74F1CE060, 8 bytes long.
 Data: <  &#210;P&#215;   > 00 00 D2 50 D7 01 00 00 
{1600626} normal block at 0x000001D750DA1230, 102 bytes long.
 Data: <<project_prefere> 3C 70 72 6F 6A 65 63 74 5F 70 72 65 66 65 72 65 
{1599904} normal block at 0x000001D74F1CE650, 8 bytes long.
 Data: < &#134;&#229;P&#215;   > 20 86 E5 50 D7 01 00 00 
..\zip\boinc_zip.cpp(122) : {299} normal block at 0x000001D74F1C3300, 260 bytes long.
 Data: <                > 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 
{284} normal block at 0x000001D74F1BF610, 80 bytes long.
 Data: </c call Scripts\> 2F 63 20 63 61 6C 6C 20 53 63 72 69 70 74 73 5C 
{283} normal block at 0x000001D74F1D5EF0, 16 bytes long.
 Data: < r O&#215;           > 98 72 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{282} normal block at 0x000001D74F1D5EA0, 16 bytes long.
 Data: <pr O&#215;           > 70 72 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{281} normal block at 0x000001D74F1D6C60, 16 bytes long.
 Data: <Hr O&#215;           > 48 72 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{280} normal block at 0x000001D74F1D64E0, 16 bytes long.
 Data: < r O&#215;           > 20 72 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{279} normal block at 0x000001D74F1D6990, 16 bytes long.
 Data: <&#248;q O&#215;           > F8 71 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{278} normal block at 0x000001D74F1D5E00, 16 bytes long.
 Data: <&#208;q O&#215;           > D0 71 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{277} normal block at 0x000001D74F1D5A50, 48 bytes long.
 Data: <ComSpec=C:\Windo> 43 6F 6D 53 70 65 63 3D 43 3A 5C 57 69 6E 64 6F 
{276} normal block at 0x000001D74F1D6850, 16 bytes long.
 Data: <H% O&#215;           > 48 25 1C 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{275} normal block at 0x000001D74F1D1790, 32 bytes long.
 Data: <SystemRoot=C:\Wi> 53 79 73 74 65 6D 52 6F 6F 74 3D 43 3A 5C 57 69 
{274} normal block at 0x000001D74F1D5F40, 16 bytes long.
 Data: < % O&#215;           > 20 25 1C 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{272} normal block at 0x000001D74F1D6620, 16 bytes long.
 Data: <&#248;$ O&#215;           > F8 24 1C 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{271} normal block at 0x000001D74F1D66C0, 16 bytes long.
 Data: <&#208;$ O&#215;           > D0 24 1C 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{270} normal block at 0x000001D74F1D6080, 16 bytes long.
 Data: <&#168;$ O&#215;           > A8 24 1C 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{269} normal block at 0x000001D74F1D6800, 16 bytes long.
 Data: < $ O&#215;           > 80 24 1C 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{268} normal block at 0x000001D74F1D6300, 16 bytes long.
 Data: <X$ O&#215;           > 58 24 1C 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{267} normal block at 0x000001D74F1D1A30, 32 bytes long.
 Data: <CUDA_DEVICE=0 PU> 43 55 44 41 5F 44 45 56 49 43 45 3D 30 00 50 55 
{266} normal block at 0x000001D74F1D62B0, 16 bytes long.
 Data: <0$ O&#215;           > 30 24 1C 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{265} normal block at 0x000001D74F1C2430, 320 bytes long.
 Data: <&#176;b O&#215;   0  O&#215;   > B0 62 1D 4F D7 01 00 00 30 1A 1D 4F D7 01 00 00 
{264} normal block at 0x000001D74F1D63F0, 16 bytes long.
 Data: <&#176;q O&#215;           > B0 71 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{263} normal block at 0x000001D74F1D6440, 16 bytes long.
 Data: < q O&#215;           > 88 71 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{262} normal block at 0x000001D74F1D1490, 32 bytes long.
 Data: <C:/Windows/syste> 43 3A 2F 57 69 6E 64 6F 77 73 2F 73 79 73 74 65 
{261} normal block at 0x000001D74F1D6D00, 16 bytes long.
 Data: <`q O&#215;           > 60 71 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{260} normal block at 0x000001D74F1D1730, 32 bytes long.
 Data: <xjvf input.tar.b> 78 6A 76 66 20 69 6E 70 75 74 2E 74 61 72 2E 62 
{259} normal block at 0x000001D74F1D6BC0, 16 bytes long.
 Data: <&#168;p O&#215;           > A8 70 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{258} normal block at 0x000001D74F1D6B20, 16 bytes long.
 Data: < p O&#215;           > 80 70 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{257} normal block at 0x000001D74F1D6350, 16 bytes long.
 Data: <Xp O&#215;           > 58 70 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{256} normal block at 0x000001D74F1D68F0, 16 bytes long.
 Data: <0p O&#215;           > 30 70 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{255} normal block at 0x000001D74F1D63A0, 16 bytes long.
 Data: < p O&#215;           > 08 70 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{254} normal block at 0x000001D74F1D6940, 16 bytes long.
 Data: <&#224;o O&#215;           > E0 6F 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{252} normal block at 0x000001D74F1D6D50, 16 bytes long.
 Data: < \ O&#215;           > 10 5C 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{251} normal block at 0x000001D74F1D5C10, 40 bytes long.
 Data: <Pm O&#215;    &#198;&#245;P&#215;   > 50 6D 1D 4F D7 01 00 00 80 C6 F5 50 D7 01 00 00 
{250} normal block at 0x000001D74F1D69E0, 16 bytes long.
 Data: <&#192;o O&#215;           > C0 6F 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{249} normal block at 0x000001D74F1D6C10, 16 bytes long.
 Data: < o O&#215;           > 98 6F 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{248} normal block at 0x000001D74F1D19D0, 32 bytes long.
 Data: <Library/usr/bin/> 4C 69 62 72 61 72 79 2F 75 73 72 2F 62 69 6E 2F 
{247} normal block at 0x000001D74F1D6CB0, 16 bytes long.
 Data: <po O&#215;           > 70 6F 1D 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{246} normal block at 0x000001D74F1D6F70, 992 bytes long.
 Data: <&#176;l O&#215;   &#208;  O&#215;   > B0 6C 1D 4F D7 01 00 00 D0 19 1D 4F D7 01 00 00 
{90} normal block at 0x000001D74F1D1970, 32 bytes long.
 Data: <windows_x86_64__> 77 69 6E 64 6F 77 73 5F 78 38 36 5F 36 34 5F 5F 
{89} normal block at 0x000001D74F1CDED0, 16 bytes long.
 Data: < &#200; O&#215;           > 20 C8 1B 4F D7 01 00 00 00 00 00 00 00 00 00 00 
{88} normal block at 0x000001D74F1BC820, 40 bytes long.
 Data: <&#208;&#222; O&#215;   p  O&#215;   > D0 DE 1C 4F D7 01 00 00 70 19 1D 4F D7 01 00 00 
{67} normal block at 0x000001D74F1CE6F0, 16 bytes long.
 Data: < &#234;&#241;&&#246;           > 80 EA F1 26 F6 7F 00 00 00 00 00 00 00 00 00 00 
{66} normal block at 0x000001D74F1CE330, 16 bytes long.
 Data: <@&#233;&#241;&&#246;           > 40 E9 F1 26 F6 7F 00 00 00 00 00 00 00 00 00 00 
{65} normal block at 0x000001D74F1CDD90, 16 bytes long.
 Data: <&#248;W&#238;&&#246;           > F8 57 EE 26 F6 7F 00 00 00 00 00 00 00 00 00 00 
{64} normal block at 0x000001D74F1CE240, 16 bytes long.
 Data: <&#216;W&#238;&&#246;           > D8 57 EE 26 F6 7F 00 00 00 00 00 00 00 00 00 00 
{63} normal block at 0x000001D74F1CE880, 16 bytes long.
 Data: <P &#238;&&#246;           > 50 04 EE 26 F6 7F 00 00 00 00 00 00 00 00 00 00 
{62} normal block at 0x000001D74F1CDD40, 16 bytes long.
 Data: <0 &#238;&&#246;           > 30 04 EE 26 F6 7F 00 00 00 00 00 00 00 00 00 00 
{61} normal block at 0x000001D74F1CE7E0, 16 bytes long.
 Data: <&#224; &#238;&&#246;           > E0 02 EE 26 F6 7F 00 00 00 00 00 00 00 00 00 00 
{60} normal block at 0x000001D74F1CDC00, 16 bytes long.
 Data: <  &#238;&&#246;           > 10 04 EE 26 F6 7F 00 00 00 00 00 00 00 00 00 00 
{59} normal block at 0x000001D74F1CE790, 16 bytes long.
 Data: <p &#238;&&#246;           > 70 04 EE 26 F6 7F 00 00 00 00 00 00 00 00 00 00 
{58} normal block at 0x000001D74F1CE2E0, 16 bytes long.
 Data: < &#192;&#236;&&#246;           > 18 C0 EC 26 F6 7F 00 00 00 00 00 00 00 00 00 00 
Object dump complete.

</stderr_txt>
]]>


©2025 Universitat Pompeu Fabra