intel / intel/llm-scaler

Intel Core Ultra 358H [B390 GPU]: vllm-scalar b8.3 failed to run Qwen3.6-A3B-AWQ INT4. RuntimeError: level_zero backend failed with error: 20

Open
#465 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
529
Forks
80
Avg merge
9h 7m
Merged PRs (30d)
38

Description

Problem #[description]
HW: Intel Core Ultra3 X7 358H
OS: Ubuntu2024.04 Kernel 6.17-intel
vllm: [llm-scaler-vllm beta release 0.14.0-b8.3](https://github.com/intel/llm-scaler/releases/tag/vllm-0.14.0-b8.3)
Model: https://www.modelscope.cn/models/QuantTrio/Qwen3.6-35B-A3B-AWQ
https://huggingface.co/QuantTrio/Qwen3.6-35B-A3B-AWQ/tree/main

Error information:
2026-06-05T03:00:47.945961799Z (EngineCore_DP0 pid=528) ERROR 06-05 03:00:47 [core.py:936] return func(*args, **kwargs)
2026-06-05T03:00:47.945962760Z (EngineCore_DP0 pid=528) ERROR 06-05 03:00:47 [core.py:936] ^^^^^^^^^^^^^^^^^^^^^
2026-06-05T03:00:47.945963963Z (EngineCore_DP0 pid=528) ERROR 06-05 03:00:47 [core.py:936] RuntimeError: level_zero backend failed with error: 20 (UR_RESULT_ERROR_DEVICE_LOST)

Image

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.