[Bug]: The API crashes after sending a chat completion request that includes seed.

[ZoneTwelve]

Your current environment

Crash after send a conversation requests that contains `seed`

Executed using the Docker image vllm-fork:9af82c
with the base gaudi image vault.habana.ai/gaudi-docker/1.19.1/ubuntu22.04/habanalabs/pytorch-installer-2.5.1:latest

services:
  worker2:
    #image: vault.habana.ai/gaudi-docker/1.19.1/ubuntu22.04/habanalabs/pytorch-installer-2.5.1:latest
    image: vllm:9af82cd
    restart: unless-stopped
    container_name: worker2
    build: .
    environment:
        - HABANA_VISIBLE_DEVICES=0
        - OMPI_MCA_btl_vader_single_copy_mechanism=none
        - VLLM_SKIP_WARMUP=${SKIP_WARMUP:-true}
    cap_add:
        - SYS_NICE
    network_mode: host
    ipc: host
    runtime: habana
    stdin_open: true
    tty: true
    volumes:
        - ./weight:/weight
    entrypoint: ["python"]
    command: -m vllm.entrypoints.openai.api_server --model /weight/llm/microsoft/phi-4 --served-model-name phi4 --port 1024

INFO 02-03 11:39:14 __init__.py:188] Automatically detected platform hpu.
Collecting environment information...
PyTorch version: 2.5.1a0+git6fc067b
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.5 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.22.1
Libc version: glibc-2.35

Python version: 3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.15.0-130-generic-x86_64-with-glibc2.35
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture:                         x86_64
CPU op-mode(s):                       32-bit, 64-bit
Address sizes:                        52 bits physical, 57 bits virtual
Byte Order:                           Little Endian
CPU(s):                               64
On-line CPU(s) list:                  0-63
Vendor ID:                            GenuineIntel
Model name:                           Intel(R) Xeon(R) Gold 6444Y
CPU family:                           6
Model:                                143
Thread(s) per core:                   2
Core(s) per socket:                   16
Socket(s):                            2
Stepping:                             7
CPU max MHz:                          4000.0000
CPU min MHz:                          800.0000
BogoMIPS:                             7200.00
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                       VT-x
L1d cache:                            1.5 MiB (32 instances)
L1i cache:                            1 MiB (32 instances)
L2 cache:                             64 MiB (32 instances)
L3 cache:                             90 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0-15,32-47
NUMA node1 CPU(s):                    16-31,48-63
Vulnerability Gather data sampling:   Not affected
Vulnerability Itlb multihit:          Not affected
Vulnerability L1tf:                   Not affected
Vulnerability Mds:                    Not affected
Vulnerability Meltdown:               Not affected
Vulnerability Mmio stale data:        Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed:               Not affected
Vulnerability Spec rstack overflow:   Not affected
Vulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

Versions of relevant libraries:
[pip3] habana-torch-dataloader==1.19.1.26
[pip3] habana-torch-plugin==1.19.1.26
[pip3] numpy==1.26.4
[pip3] pynvml==8.0.4
[pip3] pytorch-lightning==2.5.0.post0
[pip3] pyzmq==26.2.0
[pip3] torch==2.5.1a0+git6fc067b
[pip3] torch_tb_profiler==0.4.0
[pip3] torchaudio==2.5.1a0+1661daf
[pip3] torchdata==0.9.0+d4bb3e6
[pip3] torchmetrics==1.6.1
[pip3] torchtext==0.18.0a0+9bed85d
[pip3] torchvision==0.20.1a0+3ac97aa
[pip3] transformers==4.48.0
[pip3] triton==3.1.0
[conda] Could not collect
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.3.dev1911+g9af82cda
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
Could not collect

LD_LIBRARY_PATH=/usr/local/lib/python3.10/dist-packages/cv2/../../lib64:/opt/habanalabs/libfabric-1.22.0/lib:/opt/amazon/openmpi/lib:/usr/lib/habanalabs:

After deploying a Phi-4 Model on the Gaudi 2 development environment, I encountered an issue with my data generation code, resulting in the following error.

INFO:     Started server process [1]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)
INFO 02-03 11:26:07 chat_utils.py:330] Detected the chat template content format to be 'string'. You can set `--chat-template-content-format` to override this.
INFO 02-03 11:26:07 logger.py:37] Received request chatcmpl-24b6af99d31141ba82374b0ba2a31f62: prompt: "<|im_start|>system<|im_sep|>You follow the user's formatting requirements to the letter.<|im_end|><|im_start|>user<|im_sep|>根據以下主題產生 10 個相關的文章標題，格式為 <name>[title]</name>，請只回覆繁體中文：Foreignash，禁止輸出 'Foreignash' 的字串。<|im_end|><|im_start|>assistant<|im_sep|>", params: SamplingParams(n=1, presence_penalty=0.0, frequency_penalty=0.0, repetition_penalty=1.0, temperature=0.7, top_p=0.98, top_k=-1, min_p=0.0, seed=63536, stop=[], stop_token_ids=[], bad_words=[], include_stop_str_in_output=False, ignore_eos=False, max_tokens=250, min_tokens=0, logprobs=None, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True, truncate_prompt_tokens=None, guided_decoding=None), prompt_token_ids: None, lora_request: None, prompt_adapter_request: None.
INFO 02-03 11:26:07 engine.py:272] Added request chatcmpl-24b6af99d31141ba82374b0ba2a31f62.
WARNING 02-03 11:26:07 hpu_model_runner.py:1979] Configuration: (prompt, 1, 128) was not warmed-up!
WARNING 02-03 11:26:07 hpu_model_runner.py:1979] Configuration: (decode, 1, 128) was not warmed-up!
INFO 02-03 11:26:07 metrics.py:467] Avg prompt throughput: 9.5 tokens/s, Avg generation throughput: 0.1 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.1%, CPU KV cache usage: 0.0%.
ERROR 02-03 11:26:07 engine.py:138] AssertionError()
ERROR 02-03 11:26:07 engine.py:138] Traceback (most recent call last):
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/engine/multiprocessing/engine.py", line 136, in start
ERROR 02-03 11:26:07 engine.py:138]     self.run_engine_loop()
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/engine/multiprocessing/engine.py", line 199, in run_engine_loop
ERROR 02-03 11:26:07 engine.py:138]     request_outputs = self.engine_step()
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/engine/multiprocessing/engine.py", line 217, in engine_step
ERROR 02-03 11:26:07 engine.py:138]     raise e
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/engine/multiprocessing/engine.py", line 208, in engine_step
ERROR 02-03 11:26:07 engine.py:138]     return self.engine.step()
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/engine/llm_engine.py", line 1399, in step
ERROR 02-03 11:26:07 engine.py:138]     outputs = self.model_executor.execute_model(
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/executor/hpu_executor.py", line 141, in execute_model
ERROR 02-03 11:26:07 engine.py:138]     output = self.driver_worker.execute_model(execute_model_req)
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/worker/worker_base.py", line 345, in execute_model
ERROR 02-03 11:26:07 engine.py:138]     output = self.model_runner.execute_model(
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
ERROR 02-03 11:26:07 engine.py:138]     return func(*args, **kwargs)
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/worker/hpu_model_runner.py", line 2210, in execute_model
ERROR 02-03 11:26:07 engine.py:138]     output = self.model.sample(
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/worker/hpu_model_runner.py", line 417, in sample
ERROR 02-03 11:26:07 engine.py:138]     return self.model.sample(*args, **kwargs)
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/model_executor/models/llama.py", line 592, in sample
ERROR 02-03 11:26:07 engine.py:138]     next_tokens = self.sampler(logits, sampling_metadata)
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
ERROR 02-03 11:26:07 engine.py:138]     return self._call_impl(*args, **kwargs)
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1847, in _call_impl
ERROR 02-03 11:26:07 engine.py:138]     return inner()
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1793, in inner
ERROR 02-03 11:26:07 engine.py:138]     result = forward_call(*args, **kwargs)
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/model_executor/layers/sampler.py", line 299, in forward
ERROR 02-03 11:26:07 engine.py:138]     maybe_deferred_sample_results, maybe_sampled_tokens_tensor = _sample(
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/model_executor/layers/sampler.py", line 1015, in _sample
ERROR 02-03 11:26:07 engine.py:138]     return _sample_with_torch(
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/model_executor/layers/sampler.py", line 955, in _sample_with_torch
ERROR 02-03 11:26:07 engine.py:138]     multinomial_samples[sampling_type] = _multinomial(
ERROR 02-03 11:26:07 engine.py:138]   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/model_executor/layers/sampler.py", line 764, in _multinomial
ERROR 02-03 11:26:07 engine.py:138]     assert seq_group.generator is not None
ERROR 02-03 11:26:07 engine.py:138] AssertionError
CRITICAL 02-03 11:26:07 launcher.py:99] MQLLMEngine is already dead, terminating server process
INFO:     127.0.0.1:40636 - "POST /v1/chat/completions HTTP/1.1" 500 Internal Server Error
INFO:     Shutting down
INFO:     Waiting for application shutdown.
INFO:     Application shutdown complete.
INFO:     Finished server process [1]
Exception ignored in atexit callback: <bound method MetricManager._at_exit_callback of <habana_frameworks.torch.hpu.metrics.metrics.MetricManager object at 0x7f73f4916140>>
Traceback (most recent call last):
  File "/usr/local/lib/python3.10/dist-packages/habana_frameworks/torch/hpu/metrics/metrics.py", line 93, in _at_exit_callback
    def _at_exit_callback(self):
  File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.3.dev1911+g9af82cda.gaudi000-py3.10.egg/vllm/engine/multiprocessing/engine.py", line 375, in signal_handler
    raise KeyboardInterrupt("MQLLMEngine terminated")
KeyboardInterrupt: MQLLMEngine terminated

After sending the request without seed, the API server functions properly.

MITMProxy flow record:

11951:9:websocket;0:~8:response;654:6:reason;21:Internal Server Error,11:status_code;3:500#13:timestamp_end;17:1738583064.324838^15:timestamp_start;18:1738583064.3207731^8:trailers;0:~7:content;190:{"error":{"code":"bad_response_status_code","message":"Provider API error: bad response status code 500 (request id: 20250203194423578657506y281RrS6)","param":"500","type":"upstream_error"}},7:headers;259:34:6:Server,21:nginx/1.18.0 (Ubuntu),]40:4:Date,29:Mon, 03 Feb 2025 11:44:24 GMT,]51:12:Content-Type,31:application/json; charset=utf-8,]24:14:Content-Length,3:190,]28:10:Connection,10:keep-alive,]58:19:X-Oneapi-Request-Id,31:20250203194423578657506y281RrS6,]]12:http_version;8:HTTP/1.1,}7:request;1111:4:path;20:/v1/chat/completions,9:authority;0:,6:scheme;5:https,6:method;4:POST,4:port;3:443#4:host;15:localhost:1024;13:timestamp_end;18:1738583063.5385852^15:timestamp_start;17:1738583063.529074^8:trailers;0:~7:content;543:{"model": "phi4", "messages": [{"role": "system", "content": "You follow the user's formatting requirements to the letter."}, {"role": "user", "content": "\u6839\u64da\u4ee5\u4e0b\u4e3b\u984c\u7522\u751f 10 \u500b\u76f8\u95dc\u7684\u6587\u7ae0\u6a19\u984c\uff0c\u683c\u5f0f\u70ba <name>[title]</name>\uff0c\u8acb\u53ea\u56de\u8986\u7e41\u9ad4\u4e2d\u6587\uff1aredditmomentmomentx2\uff0c\u7981\u6b62\u8f38\u51fa 'redditmomentmomentx2' \u7684\u5b57\u4e32\u3002"}], "temperature": 0.7, "max_tokens": 250, "seed": 67951, "top_p": 0.98, "top_k": 5},7:headers;300:26:4:Host,15:localhost:1024,]90:13:Authorization,69:Bearer sk-V7XwmU2QRwGfbJm_I-6b_PjLmLlMxhTvYugbwVkpCrQaS2ytZ7L34jA5ptE,]15:6:Accept,3:*/*,]36:15:Accept-Encoding,13:gzip, deflate,]45:10:User-Agent,27:Python/3.10 aiohttp/3.11.11,]24:14:Content-Length,3:543,]36:12:Content-Type,16:application/json,]]12:http_version;8:HTTP/1.1,}6:backup;5950:9:websocket;0:~8:response;613:6:reason;21:Internal Server Error,11:status_code;3:500#13:timestamp_end;18:1738582490.6672142^15:timestamp_start;17:1738582490.664305^8:trailers;0:~7:content;149:{"error":{"code":"http_request_failed","message":"請求上游網址失敗 (request id: 20250203193450195044366o515hteu)","type":"unieinfra2_error"}},7:headers;259:34:6:Server,21:nginx/1.18.0 (Ubuntu),]40:4:Date,29:Mon, 03 Feb 2025 11:34:50 GMT,]51:12:Content-Type,31:application/json; charset=utf-8,]24:14:Content-Length,3:149,]28:10:Connection,10:keep-alive,]58:19:X-Oneapi-Request-Id,31:20250203193450195044366o515hteu,]]12:http_version;8:HTTP/1.1,}7:request;1111:4:path;20:/v1/chat/completions,9:authority;0:,6:scheme;5:https,6:method;4:POST,4:port;3:443#4:host;15:localhost:1024;13:timestamp_end;18:1738582490.1899142^15:timestamp_start;17:1738582490.189091^8:trailers;0:~7:content;543:{"model": "phi4", "messages": [{"role": "system", "content": "You follow the user's formatting requirements to the letter."}, {"role": "user", "content": "\u6839\u64da\u4ee5\u4e0b\u4e3b\u984c\u7522\u751f 10 \u500b\u76f8\u95dc\u7684\u6587\u7ae0\u6a19\u984c\uff0c\u683c\u5f0f\u70ba <name>[title]</name>\uff0c\u8acb\u53ea\u56de\u8986\u7e41\u9ad4\u4e2d\u6587\uff1aredditmomentmomentx2\uff0c\u7981\u6b62\u8f38\u51fa 'redditmomentmomentx2' \u7684\u5b57\u4e32\u3002"}], "temperature": 0.7, "max_tokens": 250, "seed": 67951, "top_p": 0.98, "top_k": 5},7:headers;300:26:4:Host,15:localhost:1024,]90:13:Authorization,69:Bearer sk-V7XwmU2QRwGfbJm_I-6b_PjLmLlMxhTvYugbwVkpCrQaS2ytZ7L34jA5ptE,]15:6:Accept,3:*/*,]36:15:Accept-Encoding,13:gzip, deflate,]45:10:User-Agent,27:Python/3.10 aiohttp/3.11.11,]24:14:Content-Length,3:543,]36:12:Content-Type,16:application/json,]]12:http_version;8:HTTP/1.1,}6:backup;0:~17:timestamp_created;17:1738582490.189211^7:comment;0:;8:metadata;0:}6:marked;0:;9:is_replay;0:~11:intercepted;5:false!11:server_conn;3422:3:via;0:~19:timestamp_tcp_setup;17:1738582490.161068^7:address;25:15:localhost:1024;3:443#]19:timestamp_tls_setup;17:1738582490.182026^13:timestamp_end;17:1738582490.672308^15:timestamp_start;17:1738582490.149345^3:sni;15:localhost:1024;11:tls_version;7:TLSv1.3;11:cipher_list;0:]6:cipher;22:TLS_AES_256_GCM_SHA384;11:alpn_offers;11:8:http/1.1,]4:alpn;8:http/1.1,16:certificate_list;

Model Input Dumps

No response

🐛 Describe the bug

curl http://localhost:1024/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_TOKEN" \
  -d '{
    "model": "phi4", "stream": false, "max_tokens": 500, "temperature": 0.7, "top_p": 0.98, "top_k": 5, "seed": 12345,
    "messages": [
      {"role": "system", "content": "You follow the users formatting requirements to the letter."},
      {"role": "user", "content": "Just reply with hi."}
    ]
  }'

Explanation:

The seed value in the payload may not be accepted by the server, leading to the error. You can try removing the "seed": 12345 field to resolve this issue. The error occurs because the seed parameter might conflict with the server's internal handling of random number generation or other processes. Removing the seed parameter should allow the request to be processed correctly.

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

[PatrykWo]

Hi @ZoneTwelve thanks for the issue.
I see that you are on vLLM main build.
Can you reproduce that on a tag for Gaudi marked as stable?

$ git clone https://github.com/HabanaAI/vllm-fork.git
$ cd vllm-fork
$ git checkout v0.6.4.post2+Gaudi-1.19.0

[ZoneTwelve]

Hi @ZoneTwelve thanks for the issue. I see that you are on vLLM main build. Can you reproduce that on a tag for Gaudi marked as stable?

$ git clone https://github.com/HabanaAI/vllm-fork.git $ cd vllm-fork $ git checkout v0.6.4.post2+Gaudi-1.19.0

Yes off course, I will do that for you, but that might take some time.

[ZoneTwelve]

@PatrykWo I'm sorry about the bad news.

I getting some error while running the branch you have provided and here the error.

Error log

issue-773  | Traceback (most recent call last):
issue-773  |   File "/usr/lib/python3.10/runpy.py", line 187, in _run_module_as_main
issue-773  |     mod_name, mod_spec, code = _get_module_details(mod_name, _Error)
issue-773  |   File "/usr/lib/python3.10/runpy.py", line 110, in _get_module_details
issue-773  |     __import__(pkg_name)
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.4.post2+gaudi000-py3.10.egg/vllm/__init__.py", line 7, in <module>
issue-773  |     from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.4.post2+gaudi000-py3.10.egg/vllm/engine/arg_utils.py", line 11, in <module>
issue-773  |     from vllm.config import (CacheConfig, ConfigFormat, DecodingConfig,
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.4.post2+gaudi000-py3.10.egg/vllm/config.py", line 16, in <module>
issue-773  |     from vllm.model_executor.layers.quantization import QUANTIZATION_METHODS
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.4.post2+gaudi000-py3.10.egg/vllm/model_executor/layers/quantization/__init__.py", line 5, in <module>
issue-773  |     from vllm.model_executor.layers.quantization.awq_marlin import AWQMarlinConfig
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.4.post2+gaudi000-py3.10.egg/vllm/model_executor/layers/quantization/awq_marlin.py", line 6, in <module>
issue-773  |     import vllm.model_executor.layers.fused_moe  # noqa
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.4.post2+gaudi000-py3.10.egg/vllm/model_executor/layers/fused_moe/__init__.py", line 34, in <module>
issue-773  |     import vllm.model_executor.layers.fused_moe.fused_marlin_moe  # noqa
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.4.post2+gaudi000-py3.10.egg/vllm/model_executor/layers/fused_moe/fused_marlin_moe.py", line 8, in <module>
issue-773  |     from vllm.model_executor.layers.fused_moe.fused_moe import (
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/vllm-0.6.4.post2+gaudi000-py3.10.egg/vllm/model_executor/layers/fused_moe/fused_moe.py", line 18, in <module>
issue-773  |     from vllm_hpu_extension.ops import scaled_fp8_quant
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/vllm_hpu_extension/ops.py", line 9, in <module>
issue-773  |     import habana_frameworks.torch as htorch
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/habana_frameworks/torch/__init__.py", line 54, in <module>
issue-773  |     import habana_frameworks.torch.core
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/habana_frameworks/torch/core/__init__.py", line 114, in <module>
issue-773  |     import_compilers()
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/habana_frameworks/torch/dynamo/compile_backend/backends.py", line 39, in import_compilers
issue-773  |     from .compilers import hpu_inference_compiler, hpu_training_compiler_bw, hpu_training_compiler_fw
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/habana_frameworks/torch/dynamo/compile_backend/compilers.py", line 27, in <module>
issue-773  |     from .freezing_passes import freeze
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/habana_frameworks/torch/dynamo/compile_backend/freezing_passes.py", line 28, in <module>
issue-773  |     from torch._inductor.freezing import discard_traced_gm_params, invalidate_eager_modules, replace_params_with_constants
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/torch/_inductor/freezing.py", line 15, in <module>
issue-773  |     from torch._inductor.fx_passes.freezing_patterns import freezing_passes
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/torch/_inductor/fx_passes/freezing_patterns.py", line 5, in <module>
issue-773  |     from torch._inductor.compile_fx import fake_tensor_prop
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/torch/_inductor/compile_fx.py", line 49, in <module>
issue-773  |     from torch._inductor.debug import save_args_for_compile_fx_inner
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/torch/_inductor/debug.py", line 26, in <module>
issue-773  |     from . import config, ir  # noqa: F811, this is needed
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/torch/_inductor/ir.py", line 77, in <module>
issue-773  |     from .runtime.hints import ReductionHint
issue-773  |   File "/usr/local/lib/python3.10/dist-packages/torch/_inductor/runtime/hints.py", line 36, in <module>
issue-773  |     attr_desc_fields = {f.name for f in fields(AttrsDescriptor)}
issue-773  |   File "/usr/lib/python3.10/dataclasses.py", line 1198, in fields
issue-773  |     raise TypeError('must be called with a dataclass type or instance') from None
issue-773  | TypeError: must be called with a dataclass type or instance
issue-773 exited with code 1

[PatrykWo]

@ZoneTwelve it's not bad news rather confirmation that it's not related with a build. Thanks. We are on it.