e411

我看到2026-08-21重新发布了一个使用新版本的maca的sglang 0.5.12镜像，这个镜像和之前07-22的sglang 0.5.12有何区别？和08-07发布的0.5.13版本，支持的模型有何区别？

名称版本
sglang:0.5.12-maca.ai3.8.2.7-torch2.10-py310-kylinv11-amd64
推荐安装MACA Driver 3.8.2.xsglang 0.5.12Pytorch 2.10Python 3.10
更新时间
2026-08-21 14:31:17
基本描述
提供了面向曦云C500系列的 sglang 推理运行环境，适配多个 sglang 版本，支持 DeepSeek、Kimi-K2、Qwen 等多个系列模型，可用于提供 LLM 推理和性能验证服务。

名称版本
sglang:0.5.13-maca.ai3.8.1.3-torch2.10-py312-kylinv11-amd64
推荐安装MACA Driver 3.8.1.xsglang 0.5.13Pytorch 2.10Python 3.12
更新时间
2026-08-07 19:05:52
基本描述
提供了面向曦云C500系列的 sglang 推理运行环境，适配多个 sglang 版本，支持 DeepSeek、Kimi-K2、Qwen 等多个系列模型，可用于提供 LLM 推理和性能验证服务。

名称版本
sglang:0.5.12-maca.ai3.8.0.3-torch2.8-py310-kylinv11-amd64
推荐安装MACA Driver 3.8.0.xsglang 0.5.12Pytorch 2.8Python 3.10
更新时间
2026-07-22 17:51:33
基本描述
提供了面向曦云C500系列的 sglang 推理运行环境，适配多个 sglang 版本，支持 DeepSeek、Kimi-K2、Qwen 等多个系列模型，可用于提供 LLM 推理和性能验证服务。

您好，采用的运行参数和本主题中前述参数完全一样，区别只有换用了7.16的发布版本vllm 0.22.0. 此命令在前面使用的vllm 0.21.0 poc中是可以正常运行的，所以希望您能确认下这个公开版是不是真支持dsv4了

INFO 07-20 17:29:07 [__init__.py:44] Available plugins for group vllm.platform_plugins:
INFO 07-20 17:29:07 [__init__.py:46] - metax -> vllm_metax:register
INFO 07-20 17:29:07 [__init__.py:49] All plugins in this group will be loaded. Set `VLLM_PLUGINS` to control which plugins to load.
INFO 07-20 17:29:07 [__init__.py:238] Platform plugin metax is activated
INFO 07-20 17:29:07 [envs.py:123] Plugin sets VLLM_USE_FLASHINFER_SAMPLER to False. Reason: flashinfer sampler are not supported on maca
INFO 07-20 17:29:07 [envs.py:123] Plugin sets VLLM_ENGINE_READY_TIMEOUT_S to 3600. Reason: set timeout to 3600s for model loading
INFO 07-20 17:29:07 [envs.py:123] Plugin sets VLLM_FLOAT32_MATMUL_PRECISION to high. Reason: set float32 matmul precision to high for better performance on Maca platform
INFO 07-20 17:29:07 [envs.py:123] Plugin sets VLLM_USE_V2_MODEL_RUNNER to False. Reason: v2 model runner is still under development and not fully tested on Maca platform, disable it by default
WARNING 07-20 17:29:09 [config.py:70] Support for Transformers v4 is deprecated. The Transformers v4 codepath will become unmaintained in vLLM v0.22.0 and will be removed in vLLM v0.24.0. Please upgrade to Transformers v5: pip install --upgrade transformers
INFO Print the version information of mcoplib during compilation.

Version info:Mcoplib_Version = '0.4.7'
Build_Maca_Version = '3.8.0.23'
GIT_BRANCH = 'HEAD'
GIT_COMMIT = '3c71b39'
Vllm Op Version = 0.22.0
SGlang Op Version  = 0.5.12

INFO Staring Check the current MACA version of the operating environment.

INFO: Release major.minor matching,  successful:3.8.

WARNING 07-20 17:29:28 [__init__.py:87] The quantization method 'awq' already exists and will be overwritten by the quantization config <class 'vllm_metax.quant_config.awq.MacaAWQConfig'>.
WARNING 07-20 17:29:28 [__init__.py:87] The quantization method 'awq_marlin' already exists and will be overwritten by the quantization config <class 'vllm_metax.quant_config.awq_marlin.MacaAWQMarlinConfig'>.
WARNING 07-20 17:29:28 [__init__.py:87] The quantization method 'compressed-tensors' already exists and will be overwritten by the quantization config <class 'vllm_metax.quant_config.compressed_tensors.MacaCompressedTensorsConfig'>.
WARNING 07-20 17:29:28 [__init__.py:87] The quantization method 'gptq' already exists and will be overwritten by the quantization config <class 'vllm_metax.quant_config.auto_gptq.MacaAutoGPTQConfig'>.
WARNING 07-20 17:29:28 [__init__.py:87] The quantization method 'auto_gptq' already exists and will be overwritten by the quantization config <class 'vllm_metax.quant_config.auto_gptq.MacaAutoGPTQConfig'>.
WARNING 07-20 17:29:28 [__init__.py:87] The quantization method 'moe_wna16' already exists and will be overwritten by the quantization config <class 'vllm_metax.quant_config.moe_wna16.MacaMoeWNA16Config'>.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture DeepSeekMTPModel is already registered, and will be overwritten by the new model class vllm_metax.models.deepseek_mtp:DeepSeekMTP.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture DeepseekV2ForCausalLM is already registered, and will be overwritten by the new model class vllm_metax.models.deepseek_v2:DeepseekV2ForCausalLM.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture DeepseekV3ForCausalLM is already registered, and will be overwritten by the new model class vllm_metax.models.deepseek_v2:DeepseekV3ForCausalLM.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture DeepseekV32ForCausalLM is already registered, and will be overwritten by the new model class vllm_metax.models.deepseek_v2:DeepseekV3ForCausalLM.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture GlmMoeDsaForCausalLM is already registered, and will be overwritten by the new model class vllm_metax.models.deepseek_v2:GlmMoeDsaForCausalLM.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture DeepseekV4ForCausalLM is already registered, and will be overwritten by the new model class vllm_metax.models.deepseek_v4:DeepseekV4ForCausalLM.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture DeepSeekV4MTPModel is already registered, and will be overwritten by the new model class vllm_metax.models.deepseek_v4_mtp:DeepSeekV4MTP.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture Step3p5MTP is already registered, and will be overwritten by the new model class vllm_metax.models.step3p5_mtp:Step3p5MTP.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture Qwen3OmniMoeForConditionalGeneration is already registered, and will be overwritten by the new model class vllm_metax.models.qwen3_omni_moe_thinker:Qwen3OmniMoeThinkerForConditionalGeneration.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture MiMoV2ForCausalLM is already registered, and will be overwritten by the new model class vllm_metax.models.mimo_v2:MiMoV2ForCausalLM.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture MiMoV2FlashForCausalLM is already registered, and will be overwritten by the new model class vllm_metax.models.mimo_v2:MiMoV2FlashForCausalLM.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture MiMoV2MTPModel is already registered, and will be overwritten by the new model class vllm_metax.models.mimo_v2_mtp:MiMoV2MTP.
WARNING 07-20 17:29:28 [registry.py:983] Model architecture MiMoV2OmniMTPModel is already registered, and will be overwritten by the new model class vllm_metax.models.mimo_v2_mtp:MiMoV2OmniMTP.
(APIServer pid=13) INFO 07-20 17:29:28 [utils.py:344]
(APIServer pid=13) INFO 07-20 17:29:28 [utils.py:344]        █     █     █▄   ▄█
(APIServer pid=13) INFO 07-20 17:29:28 [utils.py:344]  ▄▄ ▄█ █     █     █ ▀▄▀ █  version 0.22.0
(APIServer pid=13) INFO 07-20 17:29:28 [utils.py:344]   █▄█▀ █     █     █     █  model   /llm_models/DeepSeek-V4-Flash-FlexSMQ-AWQ-W8A8
(APIServer pid=13) INFO 07-20 17:29:28 [utils.py:344]    ▀▀  ▀▀▀▀▀ ▀▀▀▀▀ ▀     ▀
(APIServer pid=13) INFO 07-20 17:29:28 [utils.py:344]
(APIServer pid=13) INFO 07-20 17:29:28 [utils.py:278] non-default args: {'model_tag': '/llm_models/DeepSeek-V4-Flash-FlexSMQ-AWQ-W8A8', 'default_chat_template_kwargs': {'enable_thinking': True}, 'enable_auto_tool_choice': True, 'tool_call_parser': 'deepseek_v4', 'port': 8001, 'model': '/llm_models/DeepSeek-V4-Flash-FlexSMQ-AWQ-W8A8', 'tokenizer_mode': 'deepseek_v4', 'trust_remote_code': True, 'max_model_len': 512000, 'served_model_name': ['deepseek-v4-flash'], 'reasoning_parser': 'deepseek_v4', 'tensor_parallel_size': 8, 'block_size': 256, 'gpu_memory_utilization': 0.8, 'kv_cache_dtype': 'bfloat16', 'max_num_seqs': 2, 'enable_chunked_prefill': True, 'async_scheduling': True, 'compilation_config': {'mode': None, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['all'], 'ir_enable_torch_wrap': None, 'splitting_ops': None, 'compile_mm_encoder': False, 'cudagraph_mm_encoder': False, 'encoder_cudagraph_token_budgets': [], 'encoder_cudagraph_max_vision_items_per_batch': 0, 'encoder_cudagraph_max_frames_per_batch': None, 'compile_sizes': None, 'compile_ranges_endpoints': None, 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'size_asserts': False, 'alignment_asserts': False, 'scalar_asserts': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 0, 'cudagraph_capture_sizes': None, 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': None, 'pass_config': {}, 'max_cudagraph_capture_size': None, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': None, 'static_all_moe_layers': []}}
(APIServer pid=13) INFO 07-20 17:29:28 [config.py:431] Replacing legacy 'type' key with 'rope_type'
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950] Error in inspecting model architecture 'DeepseekV4ForCausalLM'
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950] Traceback (most recent call last):
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 1385, in _run_in_subprocess
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     returned.check_returncode()
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/subprocess.py", line 502, in check_returncode
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     raise CalledProcessError(self.returncode, self.args, self.stdout,
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950] subprocess.CalledProcessError: Command '['/opt/conda/bin/python3.12', '-m', 'vllm.model_executor.models.registry']' returned non-zero exit status 1.
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950] The above exception was the direct cause of the following exception:
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950] Traceback (most recent call last):
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 948, in _try_inspect_model_cls
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     return model.inspect_model_cls()
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]            ^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/site-packages/vllm/logging_utils/log_time.py", line 21, in _wrapper
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     result = func(*args, **kwargs)
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]              ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 909, in inspect_model_cls
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     mi = _run_in_subprocess(
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]          ^^^^^^^^^^^^^^^^^^^
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 1388, in _run_in_subprocess
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     raise RuntimeError(
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950] RuntimeError: Error raised in subprocess:
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950] <frozen runpy>:128: RuntimeWarning: 'vllm.model_executor.models.registry' found in sys.modules after import of package 'vllm.model_executor.models', but prior to execution of 'vllm.model_executor.models.registry'; this may result in unpredictable behaviour
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950] Traceback (most recent call last):
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "<frozen runpy>", line 198, in _run_module_as_main
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "<frozen runpy>", line 88, in _run_code
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 1411, in <module>
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     _run()
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 1404, in _run
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     result = fn()
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]              ^^^^
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 910, in <lambda>
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     lambda: _ModelInfo.from_model_cls(self.load_model_cls())
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]                                       ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/site-packages/vllm/model_executor/models/registry.py", line 923, in load_model_cls
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     mod = importlib.import_module(self.module_name)
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/importlib/__init__.py", line 90, in import_module
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     return _bootstrap._gcd_import(name[level:], package, level)
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "<frozen importlib._bootstrap>", line 1387, in _gcd_import
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "<frozen importlib._bootstrap>", line 1360, in _find_and_load
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "<frozen importlib._bootstrap>", line 1331, in _find_and_load_unlocked
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "<frozen importlib._bootstrap>", line 935, in _load_unlocked
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "<frozen importlib._bootstrap_external>", line 999, in exec_module
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/site-packages/vllm_metax/models/deepseek_v4.py", line 23, in <module>
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     from vllm_metax.customized.pluggable_layer.deepseek_v4_attention import (
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]   File "/opt/conda/lib/python3.12/site-packages/vllm_metax/customized/pluggable_layer/deepseek_v4_attention.py", line 9, in <module>
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]     from vllm.model_executor.layers.deepseek_v4_attention import (
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950] ModuleNotFoundError: No module named 'vllm.model_executor.layers.deepseek_v4_attention'
(APIServer pid=13) ERROR 07-20 17:30:00 [registry.py:950]
(APIServer pid=13) Traceback (most recent call last):
(APIServer pid=13)   File "/opt/conda/bin/vllm", line 8, in <module>
(APIServer pid=13)     sys.exit(main())
(APIServer pid=13)              ^^^^^^
(APIServer pid=13)   File "/opt/conda/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 92, in main
(APIServer pid=13)     args.dispatch_function(args)
(APIServer pid=13)   File "/opt/conda/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 148, in cmd
(APIServer pid=13)     uvloop.run(run_server(args))
(APIServer pid=13)   File "/opt/conda/lib/python3.12/site-packages/uvloop/__init__.py", line 96, in run
(APIServer pid=13)     return __asyncio.run(
(APIServer pid=13)            ^^^^^^^^^^^^^^
(APIServer pid=13)   File "/opt/conda/lib/python3.12/asyncio/runners.py", line 195, in run
(APIServer pid=13)     return runner.run(main)
(APIServer pid=13)            ^^^^^^^^^^^^^^^^
(APIServer pid=13)   File "/opt/conda/lib/python3.12/asyncio/runners.py", line 118, in run
(APIServer pid=13)     return self._loop.run_until_complete(task)
(APIServer pid=13)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=13)   File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
(APIServer pid=13)   File "/opt/conda/lib/python3.12/site-packages/uvloop/__init__.py", line 48, in wrapper
(APIServer pid=13)     return await main
(APIServer pid=13)            ^^^^^^^^^^
(APIServer pid=13)   File "/opt/conda/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 678, in run_server
(APIServer pid=13)     await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)
(APIServer pid=13)   File "/opt/conda/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 692, in run_server_worker
(APIServer pid=13)     async with build_async_engine_client(
(APIServer pid=13)                ^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=13)   File "/opt/conda/lib/python3.12/contextlib.py", line 210, in __aenter__
(APIServer pid=13)     return await anext(self.gen)
(APIServer pid=13)            ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=13)   File "/opt/conda/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 100, in build_async_engine_client
(APIServer pid=13)     async with build_async_engine_client_from_engine_args(
(APIServer pid=13)                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=13)   File "/opt/conda/lib/python3.12/contextlib.py", line 210, in __aenter__
(APIServer pid=13)     return await anext(self.gen)
(APIServer pid=13)            ^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=13)   File "/opt/conda/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 124, in build_async_engine_client_from_engine_args
(APIServer pid=13)     vllm_config = engine_args.create_engine_config(usage_context=usage_context)
(APIServer pid=13)                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=13)   File "/opt/conda/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1730, in create_engine_config
(APIServer pid=13)     model_config = self.create_model_config()
(APIServer pid=13)                    ^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=13)   File "/opt/conda/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 1560, in create_model_config
(APIServer pid=13)     return ModelConfig(
(APIServer pid=13)            ^^^^^^^^^^^^
(APIServer pid=13)   File "/opt/conda/lib/python3.12/site-packages/pydantic/_internal/_dataclasses.py", line 121, in __init__
(APIServer pid=13)     s.__pydantic_validator__.validate_python(ArgsKwargs(args, kwargs), self_instance=s)
(APIServer pid=13) pydantic_core._pydantic_core.ValidationError: 1 validation error for ModelConfig
(APIServer pid=13)   Value error, Model architectures ['DeepseekV4ForCausalLM'] failed to be inspected. Please check the logs for more details. [type=value_error, input_value=ArgsKwargs((), {'model': ...nderer_num_workers': 1}), input_type=ArgsKwargs]
(APIServer pid=13)     For further information visit https://errors.pydantic.dev/2.13/v/value_error

您好，部署按照之前命令无法成功，请你再确认一下

vllm-metax:0.22.0 7月16发布的这个新版本是否支持deepseek v4了？

你们现在有比较新的dsv4的验证镜像吗，我这边真的很想部署一个dsv4来用（

注意到vllm镜像里的tilelang没有maca适配代码

我进一步排查后，发现其中的tilelang有问题，我对比了贵公司官网发布的tilelang安装包与vllm镜像内的tilelang，发现vllm镜像内tilelang是上游版本，而不是贵公司适配过的tilelang maca版本，其中不含任何maca代码，只有cuda，vllm调用到了cuda，导致maca工具链编译报错，请联系贵公司研发重新适配打包这个vllm的镜像，谢谢！

没有变化，日志仍然是之前一样。

source /etc/profile.d/conda.sh 是为了加载vllm所在的虚拟环境，因为docker run -d拉起来的bash是非交互的，因此不会自动加载conda环境，为了正确加载后续vllm命令，必须加载一下conda.sh。

[Wed Jul  1 22:58:53 2026] AMD-Vi: Disabling interrupt remapping
[Wed Jul  1 22:58:54 2026] ACPI: Using IOAPIC for interrupt routing
[Wed Jul  1 22:58:54 2026] ACPI: PCI: Interrupt link LNKA configured for IRQ 0
[Wed Jul  1 22:58:54 2026] ACPI: PCI: Interrupt link LNKB configured for IRQ 0
[Wed Jul  1 22:58:54 2026] ACPI: PCI: Interrupt link LNKC configured for IRQ 0
[Wed Jul  1 22:58:54 2026] ACPI: PCI: Interrupt link LNKD configured for IRQ 0
[Wed Jul  1 22:58:54 2026] ACPI: PCI: Interrupt link LNKE configured for IRQ 0
[Wed Jul  1 22:58:54 2026] ACPI: PCI: Interrupt link LNKF configured for IRQ 0
[Wed Jul  1 22:58:54 2026] ACPI: PCI: Interrupt link LNKG configured for IRQ 0
[Wed Jul  1 22:58:54 2026] ACPI: PCI: Interrupt link LNKH configured for IRQ 0
[Wed Jul  1 22:58:57 2026] RAS: Correctable Errors collector initialized.
[Wed Jul  1 22:59:12 2026] hrtimer: interrupt took 30958313 ns

我认为这和卡没有任何关系，是vllm metax内部的一些软件错误

一、软硬件信息
1.服务器厂家: 超云
2.沐曦GPU型号： C500
3.操作系统内核版本： 6.8.0-124-generic
4.是否开启CPU虚拟化：是
5.mx-smi回显：

mx-smi  version: 2.3.4

=================== MetaX System Management Interface Log ===================
Timestamp                                         : Wed Jul  1 23:56:36 2026

Attached GPUs                                     : 8
+---------------------------------------------------------------------------------+
| MX-SMI 2.3.4                       Kernel Mode Driver Version: 3.9.10           |
| MACA Version: 3.7.0.38             BIOS Version: 1.35.2.0                       |
|------------------+-----------------+---------------------+----------------------|
| Board       Name | GPU   Persist-M | Bus-id              | GPU-Util      sGPU-M |
| Pwr:Usage/Cap    | Temp       Perf | Memory-Usage        | GPU-State            |
|==================+=================+=====================+======================|
| 0     MetaX C500 | 0           Off | 0000:04:00.0        | 0%          Disabled |
| 38W / 350W       | 40C          P0 | 860/65536 MiB       | Available            |
+------------------+-----------------+---------------------+----------------------+
| 1     MetaX C500 | 1           Off | 0000:05:00.0        | 0%          Disabled |
| 39W / 350W       | 41C          P0 | 860/65536 MiB       | Available            |
+------------------+-----------------+---------------------+----------------------+
| 2     MetaX C500 | 2           Off | 0000:06:00.0        | 0%          Disabled |
| 42W / 350W       | 43C          P0 | 860/65536 MiB       | Available            |
+------------------+-----------------+---------------------+----------------------+
| 3     MetaX C500 | 3           Off | 0000:07:00.0        | 0%          Disabled |
| 38W / 350W       | 41C          P0 | 860/65536 MiB       | Available            |
+------------------+-----------------+---------------------+----------------------+
| 4     MetaX C500 | 4           Off | 0000:0b:00.0        | 0%          Disabled |
| 40W / 350W       | 42C          P0 | 860/65536 MiB       | Available            |
+------------------+-----------------+---------------------+----------------------+
| 5     MetaX C500 | 5           Off | 0000:0c:00.0        | 0%          Disabled |
| 41W / 350W       | 43C          P0 | 860/65536 MiB       | Available            |
+------------------+-----------------+---------------------+----------------------+
| 6     MetaX C500 | 6           Off | 0000:0d:00.0        | 0%          Disabled |
| 42W / 350W       | 41C          P0 | 860/65536 MiB       | Available            |
+------------------+-----------------+---------------------+----------------------+
| 7     MetaX C500 | 7           Off | 0000:0e:00.0        | 0%          Disabled |
| 39W / 350W       | 40C          P0 | 860/65536 MiB       | Available            |
+------------------+-----------------+---------------------+----------------------+

+---------------------------------------------------------------------------------+
| Process:                                                                        |
|  GPU                    PID         Process Name                 GPU Memory     |
|                                                                  Usage(MiB)     |
|=================================================================================|
|  no process found                                                               |
+---------------------------------------------------------------------------------+

End of Log

6.docker info回显：

Client: Docker Engine - Community
 Version:    29.3.0
 Context:    default
 Debug Mode: false
 Plugins:
  buildx: Docker Buildx (Docker Inc.)
    Version:  v0.31.1
    Path:     /usr/libexec/docker/cli-plugins/docker-buildx
  compose: Docker Compose (Docker Inc.)
    Version:  v5.1.0
    Path:     /usr/libexec/docker/cli-plugins/docker-compose
  model: Docker Model Runner (Docker Inc.)
    Version:  v1.1.8
    Path:     /usr/libexec/docker/cli-plugins/docker-model

Server:
 Containers: 12
  Running: 4
  Paused: 0
  Stopped: 8
 Images: 15
 Server Version: 29.3.0
 Storage Driver: overlayfs
  driver-type: io.containerd.snapshotter.v1
 Logging Driver: json-file
 Cgroup Driver: systemd
 Cgroup Version: 2
 Plugins:
  Volume: local
  Network: bridge host ipvlan macvlan null overlay
  Log: awslogs fluentd gcplogs gelf journald json-file local splunk syslog
 CDI spec directories:
  /etc/cdi
  /var/run/cdi
 Swarm: inactive
 Runtimes: io.containerd.runc.v2 runc
 Default Runtime: runc
 Init Binary: docker-init
 containerd version: dea7da592f5d1d2b7755e3a161be07f43fad8f75
 runc version: v1.3.4-0-gd6d73eb8
 init version: de40ad0
 Security Options:
  apparmor
  seccomp
   Profile: builtin
  cgroupns
 Kernel Version: 6.8.0-124-generic
 Operating System: Ubuntu-Server 24.04.4 LTS (Noble Numbat)
 OSType: linux
 Architecture: x86_64
 CPUs: 192
 Total Memory: 503.5GiB
 Name: server2
 ID: 404bb473-c286-41a5-a18e-b94481c6f73e
 Docker Root Dir: /var/lib/docker
 Debug Mode: false
 Experimental: false
 Insecure Registries:
  ::1/128
  127.0.0.0/8
 Live Restore Enabled: false
 Firewall Backend: iptables

7.镜像版本：cr.metax-tech.com/public-ai-release/maca/vllm-metax:0.21.0-maca.ai3.7.1.106-torch2.8-py312-ubuntu22.04-amd64
8.启动容器命令：

docker run -d \
    --device=/dev/dri \
    --device=/dev/mxcd \
    --device=/dev/infiniband \
    --group-add video \
    --security-opt seccomp=unconfined \
    --security-opt apparmor=unconfined \
    --shm-size 100gb \
    --ulimit memlock=-1 \
    --privileged=true \
    --network host \
    -v /mnt/modelscope:/llm_models \
    --name vllm-deepseek-v4-flash \
    cr.metax-tech.com/public-ai-release/maca/vllm-metax:0.21.0-maca.ai3.7.1.106-torch2.8-py312-ubuntu22.04-amd64 bash -c "source /etc/profile.d/conda.sh && source /llm_models/run-deepseek-v4-entry.sh"

9.容器内执行命令（/llm_models/run-deepseek-v4-entry.sh的内容）：

#!/bin/bash
export MACA_SMALL_PAGESIZE_ENABLE=1
export MACA_VLLM_ENABLE_MCTLASS_FUSED_MOE=0
export MACA_VLLM_ENABLE_MCTLASS_PYTHON_API=1

vllm serve /llm_models/DeepSeek-V4-Flash-FlexSMQ-AWQ-W8A8 --served-model-name DeepSeek-V4-Flash --trust-remote-code \
--kv-cache-dtype bfloat16 --block-size 256 --port 8001 --max-model-len 1048576 --gpu-memory-utilization 0.9 \
--tokenizer-mode deepseek_v4 --tool-call-parser deepseek_v4 \
--enable-auto-tool-choice --reasoning-parser deepseek_v4 --default-chat-template-kwargs '{"enable_thinking": true}' \
--compilation-config '{"cudagraph_mode":"FULL_AND_PIECEWISE", "custom_ops":["all"]}' \
--max-num-seq 32 -tp 8 --speculative_config '{"method": "mtp", "num_speculative_tokens": 1}'

二、问题现象
请描述详细的问题现象日志。若日志过长，请上传附件(txt格式）。

硬件 C500 * 8

我使用的命令是：

#!/bin/bash
export MACA_SMALL_PAGESIZE_ENABLE=1
export MACA_VLLM_ENABLE_MCTLASS_FUSED_MOE=0
export MACA_VLLM_ENABLE_MCTLASS_PYTHON_API=1

vllm serve /llm_models/DeepSeek-V4-Flash-FlexSMQ-AWQ-W8A8 --served-model-name DeepSeek-V4-Flash --trust-remote-code \
--kv-cache-dtype bfloat16 --block-size 256 --port 8001 --max-model-len 1048576 --gpu-memory-utilization 0.9 \
--tokenizer-mode deepseek_v4 --tool-call-parser deepseek_v4 \
--enable-auto-tool-choice --reasoning-parser deepseek_v4 --default-chat-template-kwargs '{"enable_thinking": true}' \
--compilation-config '{"cudagraph_mode":"FULL_AND_PIECEWISE", "custom_ops":["all"]}' \
--max-num-seq 32 -tp 8 --speculative_config '{"method": "mtp", "num_speculative_tokens": 1}'

然后在加载完模型之后产生巨量的tilelang的编译报错，然后失败退出

sudo sh metax-driver-3.8.0.10-deb-x86_64.run
[sudo] password for cast503:
Verifying archive integrity...  100%   MD5 checksums are OK. All good.
Uncompressing MetaX driver installer  100%
uninstalling metax-linux-dkms
(Reading database ... 142019 files and directories currently installed.)
Removing metax-linux-dkms (3.8.30) ...
Module metax-linux-3.8.30 for kernel 6.8.0-110-generic (x86_64).
Before uninstall, this module version was ACTIVE on this kernel.

metax.ko.zst:
 - Uninstallation
   - Deleting from: /lib/modules/6.8.0-110-generic/updates/dkms/
 - Original module
   - No original module was found for this module on this kernel.
   - Use the dkms install command to reinstall any previous module version.

Running the post_remove script:
depmod....
Module metax-linux-3.8.30 for kernel 6.8.0-124-generic (x86_64).
Before uninstall, this module version was ACTIVE on this kernel.

metax.ko.zst:
 - Uninstallation
   - Deleting from: /lib/modules/6.8.0-124-generic/updates/dkms/
 - Original module
   - No original module was found for this module on this kernel.
   - Use the dkms install command to reinstall any previous module version.

Running the post_remove script:
depmod....
Deleting module metax-linux-3.8.30 completely from the DKMS tree.
uninstalling mxsmt
(Reading database ... 141807 files and directories currently installed.)
Removing mxsmt (3.7.2.30) ...
mxsmt package uninstalled successfully
Purging configuration files for mxsmt (3.7.2.30) ...
mxsmt package uninstalled successfully
dpkg: warning: while removing mxsmt, directory '/opt/mxdriver' not empty so not removed
uninstalling mxfw
(Reading database ... 141795 files and directories currently installed.)
Removing mxfw (3.7.2) ...
mxfw package uninstalled successfully
Purging configuration files for mxfw (3.7.2) ...
mxfw package uninstalled successfully

deb/mxfw_*.deb
deb/mxsmt_*.deb
deb/metax-linux[-_]*.deb
installing packages under /opt/mxdriver
installing deb/mxfw_3.8.0-1.all.deb
Selecting previously unselected package mxfw.
(Reading database ... 141709 files and directories currently installed.)
Preparing to unpack deb/mxfw_3.8.0-1.all.deb ...
Unpacking mxfw (3.8.0) ...
Setting up mxfw (3.8.0) ...
mxfw package installed successfully
installing deb/mxsmt_3.8.0.10.amd64.deb
Selecting previously unselected package mxsmt.
(Reading database ... 141795 files and directories currently installed.)
Preparing to unpack deb/mxsmt_3.8.0.10.amd64.deb ...
Unpacking mxsmt (3.8.0.10) ...
Setting up mxsmt (3.8.0.10) ...
mxsmt package installed successfully
Processing triggers for libc-bin (2.39-0ubuntu8.7) ...
installing deb/metax-linux_3.9.10-1_amd64.deb
Selecting previously unselected package metax-linux.
(Reading database ... 141807 files and directories currently installed.)
Preparing to unpack .../metax-linux_3.9.10-1_amd64.deb ...
Unpacking metax-linux (3.9.10) ...
Setting up metax-linux (3.9.10) ...

Notice: The current kernel version (6.8.0-124-generic) is not supported.
Please upgrade your kernel to one of the following versions:
5.10.0-0.deb10.28-amd64
5.10.0-29-amd64
5.10.0-30-amd64
5.10.200-4-velinux1u1-amd64
5.15.0-100-generic
5.15.0-105-generic
5.15.0-112-generic
5.15.0-119-generic
5.15.0-124-generic
5.15.0-130-generic
5.15.0-138-generic
5.15.0-25-generic
5.15.0-46-generic
5.15.0-58-generic
5.15.0-60-generic
5.15.0-72-generic
5.15.0-78-generic
5.15.0-88-generic
5.15.119-rt65-home-ear1.1
5.19.0-46-generic
5.19.17
5.4.0-131-generic
5.4.0-144-generic
5.4.0-148-generic
5.4.0-176-generic
5.4.0-26-generic
5.4.0-42-generic
5.4.18-142-generic
6.1.141-1-generic
6.1.152-1-generic
6.12.34-1-generic
6.12.47-1-generic
6.14.0-1003-oem
6.14.0-27-generic
6.8.0-31-generic
6.8.0-49-generic
6.8.0-53-generic
And then reinstall the metax-linux package.

dpkg: error processing package metax-linux (--install):
 installed metax-linux package post-installation script subprocess returned error exit status 1
Errors were encountered while processing:
 metax-linux
uninstalling metax-linux
(Reading database ... 141924 files and directories currently installed.)
Removing metax-linux (3.9.10) ...
metax-linux package uninstalled successfully
Purging configuration files for metax-linux (3.9.10) ...
metax-linux package uninstalled successfully
Reading package lists... Done
Building dependency tree... Done
Reading state information... Done
dkms is already the newest version (3.0.11-1ubuntu13).
autoconf is already the newest version (2.71-3).
automake is already the newest version (1:1.16.5-1.3ubuntu1).
The following packages were automatically installed and are no longer required:
  libdebuginfod-common libdebuginfod1t64 libfwupd2 libgusb2 libmspack0t64 libxmlsec1t64 libxmlsec1t64-openssl
  libxslt1.1 zerofree
Use 'sudo apt autoremove' to remove them.
0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
Selecting previously unselected package metax-linux-dkms.
(Reading database ... 141807 files and directories currently installed.)
Preparing to unpack .../metax-linux-dkms_3.9.10-1_amd64.deb ...
Unpacking metax-linux-dkms (3.9.10) ...
Setting up metax-linux-dkms (3.9.10) ...
Loading new metax-linux-3.9.10 DKMS files...
Building for 6.8.0-124-generic
Building for architecture x86_64
Building initial module for 6.8.0-124-generic
autoreconf: export WARNINGS=
autoreconf: Entering directory '.'
autoreconf: configure.ac: not using Gettext
autoreconf: running: aclocal --force
autoreconf: configure.ac: tracing
autoreconf: configure.ac: not using Libtool
autoreconf: configure.ac: not using Intltool
autoreconf: configure.ac: not using Gtkdoc
autoreconf: running: /usr/bin/autoconf --force
configure.ac:23: warning: The macro `AC_HELP_STRING' is obsolete.
configure.ac:23: You should run autoupdate.
./lib/autoconf/general.m4:204: AC_HELP_STRING is expanded from...
./lib/autoconf/general.m4:1534: AC_ARG_ENABLE is expanded from...
m4/config.m4:14: AC_METAX_CONFIG is expanded from...
configure.ac:23: the top level
autoreconf: running: /usr/bin/autoheader --force
autoreconf: configure.ac: not using Automake
autoreconf: 'config/install-sh' is updated
autoreconf: Leaving directory '.'
ERROR (dkms apport): unable to determine source package for metax-linux-dkms
Error! Bad return status for module build on kernel: 6.8.0-124-generic (x86_64)
Consult /var/lib/dkms/metax-linux/3.9.10/build/make.log for more information.
dpkg: error processing package metax-linux-dkms (--install):
 installed metax-linux-dkms package post-installation script subprocess returned error exit status 10
Errors were encountered while processing:
 metax-linux-dkms
ERROR: failed to install deb/metax-linux_3.9.10-1_amd64.deb

错误原因：metax-linux-3.9.10/common/mx_devinfo_c500.h 中代码有问题：

#define MX_DEV_PCI_C500_LIST    \
MX_DEV_PCI_C500(0x9999, 0x4001, 0x4019, c500, MXC500, mx_devinfo_c500)     \
MX_DEV_PCI_C500(0x9999, 0x4000, 0x4018, c550, MXC550, mx_devinfo_c550)     \
MX_DEV_PCI_C500(0x9999, 0x4083, 0x409b, n260, MXN260, mx_devinfo_n260)     \
MX_DEV_PCI_C500(0x9999, 0x4040, 0x4058, c500x, MXC500X, mx_devinfo_c500x)  \
MX_DEV_PCI_C500(0x9999, 0x4020, 0x4038, c588, MXC588, mx_devinfo_c588)

正确的代码应该是：

#define MX_DEV_PCI_C500_LIST    \
MX_DEV_PCI_C500(0x9999, 0x4001, 0x4019, c500, "MXC500", mx_devinfo_c500)     \
MX_DEV_PCI_C500(0x9999, 0x4000, 0x4018, c550, "MXC550", mx_devinfo_c550)     \
MX_DEV_PCI_C500(0x9999, 0x4083, 0x409b, n260, "MXN260", mx_devinfo_n260)     \
MX_DEV_PCI_C500(0x9999, 0x4040, 0x4058, c500x, "MXC500X", mx_devinfo_c500x)  \
MX_DEV_PCI_C500(0x9999, 0x4020, 0x4038, c588, "MXC588", mx_devinfo_c588)

也就是说倒数第二个参数本应是字符串，双引号都丢失了

据我了解，并发多了之后，华为的机器也未必就很快，体验也就一般般。910b的算力和带宽都和沐曦差不多的

至于npu的占用，这个应该是不同的厂家配置的占用率的算法不一样，没法直接比较，尤其是华为是npu，沐曦是gpu，架构差距很大，两个指标没法直接比较

用sglang部署，开MTP，开speculative V2。我这里4*C500用sglang部署qwen3.6 27b，可以达到单请求80token/s左右，8请求总吞吐应该有300token/s左右，1个请求能跑个40左右，也能接受。vllm-metax的qwen的MTP是坏的，打开推理结果会乱码

大模型推理的任务特性就决定了他的gpu占用率不会特别高。qwen3.6 27b已经是密度比较大的了，这占用还比较高，如果是那些moe模型更难跑高。通讯、数据等等占了大头

我运行是没跑起来，提示算子重复注册