From 5c69e32abe013fa1b913022682a3104c79105f37 Mon Sep 17 00:00:00 2001 From: amote-i <49533125+amote-i@users.noreply.github.com> Date: Sun, 20 Sep 2026 15:15:58 +0800 Subject: [PATCH] [NPU] [DOC] fix typos, heading levels and terminology in NPU docs (#40402) --- .../ascend-npus/development/operator_development.mdx | 8 ++++---- .../ascend-npus/evaluation/accuracy_evaluation.mdx | 1 + docs/docs/hardware-platforms/ascend-npus/faq.mdx | 8 ++++---- .../ascend-npus/mindspore_backend.mdx | 12 ++++++------ .../ascend-npus/optimization/ring_sp_performance.mdx | 2 +- docs/docs/supported-models/mindspore_models.mdx | 2 +- 6 files changed, 17 insertions(+), 16 deletions(-) diff --git a/docs/docs/hardware-platforms/ascend-npus/development/operator_development.mdx b/docs/docs/hardware-platforms/ascend-npus/development/operator_development.mdx index 979aa65ee..9dee53fbc 100644 --- a/docs/docs/hardware-platforms/ascend-npus/development/operator_development.mdx +++ b/docs/docs/hardware-platforms/ascend-npus/development/operator_development.mdx @@ -37,7 +37,7 @@ sgl-kernel-npu/ │ ├── op_host/ # Host-side code (validation, tiling, launch) │ │ ├── .cpp │ │ └── tiling/ # Optional: tiling data -│ └── op_kernel/ # Device-side code (Ascend C kernel on AICore) +│ └── op_kernel/ # Device-side code (Ascend C kernel on AI Core) │ └── _kernel.cpp ├── include/ │ └── sgl_kenel_npu_ops.h # C++ interface declarations @@ -62,7 +62,7 @@ sgl-kernel-npu/ A complete Ascend C operator consists of two parts: -- **Device part**: Kernel code running on the NPU AICore, responsible for actual +- **Device part**: Kernel code running on the NPU AI Core, responsible for actual computation. Written using the Ascend C API. - **Host part**: Code running on the CPU, responsible for parameter validation, data pre-processing, tiling, and kernel launch. @@ -86,7 +86,7 @@ csrc// ### Step 2: Write the Device-side Kernel (op_kernel) -Device-side code runs on AICore and follows the Ascend C programming model. The +Device-side code runs on AI Core and follows the Ascend C programming model. The core structure is a class with `Init()` and `Process()` methods, plus an `extern "C"` entry function. @@ -155,7 +155,7 @@ extern "C" __global__ __aicore__ void helloworld( **Key points:** -- Class methods must be marked with `__aicore__`, indicating they run on AICore. +- Class methods must be marked with `__aicore__`, indicating they run on AI Core. - Use `AscendC::TPipe` + `AscendC::TQue` to build a pipeline that overlaps data movement and computation. - The entry function must be declared `extern "C" __global__ __aicore__`. The diff --git a/docs/docs/hardware-platforms/ascend-npus/evaluation/accuracy_evaluation.mdx b/docs/docs/hardware-platforms/ascend-npus/evaluation/accuracy_evaluation.mdx index 6406b1723..5b441474e 100644 --- a/docs/docs/hardware-platforms/ascend-npus/evaluation/accuracy_evaluation.mdx +++ b/docs/docs/hardware-platforms/ascend-npus/evaluation/accuracy_evaluation.mdx @@ -267,6 +267,7 @@ This is a common workaround for corporate proxy environments. If it does not res If you cannot obtain the CA certificate, download datasets manually as shown in [Download Dataset Error](#download-dataset-error) below. ### EvalScope Request Retry Timeout + If EvalScope keeps retrying requests with errors like: ``` 2026-06-22 03:09:03 - evalscope - WARNING: Attempt 4 / 5 failed: ....... Retrying... diff --git a/docs/docs/hardware-platforms/ascend-npus/faq.mdx b/docs/docs/hardware-platforms/ascend-npus/faq.mdx index 2e803d201..8d602e828 100644 --- a/docs/docs/hardware-platforms/ascend-npus/faq.mdx +++ b/docs/docs/hardware-platforms/ascend-npus/faq.mdx @@ -42,13 +42,13 @@ Thread 0x0000fff873f6f120 (most recent call first): (SGLangEngine pid=3872176) [ERROR] 2026-04-14-12:14:41 (PID:3874122, Device:0, RankID:-1) ERR00100 PTA call acl api failed (SGLangEngine pid=3872176) [Error]: An internal error occurs in the runtime module on the host. (SGLangEngine pid=3872176) Rectify the fault based on the error information in the ascend log. -(SGLangEngine pid=3872176) [PID: 3874122] 2026-04-14-12:14:41.897.548 AclNN_Runtime_Error(EZ9903): aclrtLaunchKerneWithHostArgs failed, return: 507000 +(SGLangEngine pid=3872176) [PID: 3874122] 2026-04-14-12:14:41.897.548 AclNN_Runtime_Error(EZ9903): aclrtLaunchKernelWithHostArgs failed, return: 507000 (SGLangEngine pid=3872176) Solution: In this scenario, collect the plog when the fault occurs and locate the fault based on the plog. (SGLangEngine pid=3872176) TraceBack (most recent call last): (SGLangEngine pid=3872176) Check kernel task failed, stream_id=2028, task_id=48, retCode=0x7080005.[FUNC:LaunchKernel][FILE:context.cc][LINE:1585] (SGLangEngine pid=3872176) rtsLaunchKernelWithHostArgs execution failed, reason=kernel type error[FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:61] (SGLangEngine pid=3872176) rtsLaunchKernelWithHostArgs failed, runtime result = 507000.[FUNC:ReportCallError][FILE:Log_inner.cpp][LINE:148] -(SGLangEngine pid=3872176) aclrtLaunchKerneWWithHostArgs failed, return: 507000 +(SGLangEngine pid=3872176) aclrtLaunchKernelWithHostArgs failed, return: 507000 (SGLangEngine pid=3872176) Launch kernel failed. (SGLangEngine pid=3872176) #### KernelLaunch failed: /home/850b160/cann-8.5.8/opp/built-in/op_impl/ai_core/tbe//kernel/ascend910_93/ops_legacy/fill/Fill_41dadce325bOf810d03359af2a38990b_high_performance.o (SGLangEngine pid=3872176) Kernel Run failed. opType: 18, Fill @@ -109,7 +109,7 @@ prefill 7.log:3094:RuntimeError: ACL stream synchronize failed, error code:50703 [ERROR] RUNTIME(164629,):2026-04-14-05:34:12.381.705 davinci kernel task.cc:14241170327 GetArasInfo:[AIC INFO] aras(0 to 9) after execute:0x3fffffb9000, 0, 0, 0x12c9323ff600, 0x12c93231ee00, 0x12c93f1d8800,0x12c93f3ff600,0x12c958200000,0x100000003, 0xaaaa00000001. [ERROR] RUNTIME(164629,):2026-04-14-05:34:12.381.710 [davinci kernel task.cc:1427]170327 GetArgsInfo:tilingKey = 0, print 1 Times totalLen=(10*8), argsSize=80, blockDim=3 [ERROR] RUNTIME(164629,):2026-04-14-05:34:12.381.717 [davinci kernel task.cc:1468]170327 PrintErrorInfoForDavinciTask:[AIC INFO] after execute:arqs print end -[ERROR] RUNTIME(164629,):2026-04-14-05:34:12.381.751 davinci kernel task.cc:14981170327 PrintErrorInfoForDavinciTask:[DFX INFO]Aicore kernel execute failed, device id=13, stream id=43, report stream id=43, task id=13145, flip num=56, fault kernel_name=alloc_extend _kernel_18, fault kernel info ext=alloc_extend_kernel, program id=141, hash=14069671779787989248. +[ERROR] RUNTIME(164629,):2026-04-14-05:34:12.381.751 davinci kernel task.cc:14981170327 PrintErrorInfoForDavinciTask:[DFX INFO]Aicore kernel execute failed, device id=13, stream id=43, report stream id=43, task id=13145, flip num=56, fault kernel_name=alloc_extend_kernel_18, fault kernel info ext=alloc_extend_kernel, program id=141, hash=14069671779787989248. [ERROR] IDEDD(164629,):2026-04-14-05:34:12.381.823 [dump manager.cpp:41][tid:170327] An exception callback message is received. [ERROR] IDEDD(164629,):2026-04-14-05:34:12.381.971 [kernel info collector.cpp:384][tid:170327] Get error register information. coreNum=0 [ERROR] IDEDD(164629,):2026-04-14-05:34:12.381.981 kernel info collector.cpp:4771tid:1703271 It is Non-SuperKernel. functionCount=1, qlobalCount=1 @@ -119,7 +119,7 @@ prefill 7.log:3094:RuntimeError: ACL stream synchronize failed, error code:50703 [ERROR] RUNTIME(164629,):2026-04-14-05:34:12.383.911 [stream.cc:1335]170327 GetError:AIV Kernel happen error, retCode=0x31. [ERROR] RUNTIME(164629,):2026-04-14-05:34:12.383.929 [stream.cc:1335]170327 GetError:[AIC_INFO] after execute:args print end [ERROR] RUNTIME(164629,):2026-04-14-05:34:12.383.936 stream.cc:13351170327 GetError: DFX INFO1Aicore kernel execute failed, device id=13, stream id=43, report stream id=43, task id=13145, tlip num=56, - fault kernel_name=alloc_extend_kernel_18, ault kernel info ext=alloc_extend_kernel, program id=141, hash=14069671779787989248. + fault kernel_name=alloc_extend_kernel_18, fault kernel info ext=alloc_extend_kernel, program id=141, hash=14069671779787989248. [ERROR] RUNTIME(164629,):2026-04-14-05:34:12.383.943 [stream.cc:3549]170327 EnterFailureAbort:stream id=43 enter failure abort. [ERROR] RUNTIME(164629,):2026-04-14-05:34:12.383.973 [stars_engine.cc:1427]170327 StarsResumeRtsa:stop scheduling in abort failure mode: stream id=43, sq id=6,sq head=801, task id=13145, taskType=66. [ERROR] RUNTIME(164629,):2026-04-14-05:34:12.383.972 [stream.cc:1463]164629 SynchronizeExecutedTask:context is abort, status=0x715005e. diff --git a/docs/docs/hardware-platforms/ascend-npus/mindspore_backend.mdx b/docs/docs/hardware-platforms/ascend-npus/mindspore_backend.mdx index b242eefa8..2988c0e9f 100644 --- a/docs/docs/hardware-platforms/ascend-npus/mindspore_backend.mdx +++ b/docs/docs/hardware-platforms/ascend-npus/mindspore_backend.mdx @@ -33,9 +33,9 @@ pip install -e . Current SGLang-MindSpore supports Qwen3 and DeepSeek V3/R1 models. This doc uses Qwen3-8B as an example. -### Offline infer +### Offline Inference -Use the following script for offline infer: +Use the following script for offline inference: ```python Offline Inference @@ -107,7 +107,7 @@ python3 -m sglang.launch_server \ ## Troubleshooting -#### Debug Mode +### Debug Mode Enable sglang debug logging by log-level argument. @@ -132,7 +132,7 @@ export GLOG_v=0 # DEBUG ``` -#### Explicitly select devices +### Explicitly select devices Use the following environment variable to explicitly select the devices to use. @@ -142,7 +142,7 @@ export ASCEND_RT_VISIBLE_DEVICES=4,5,6,7 # to set device ``` -#### Some communication environment issues +### Some communication environment issues In case of some environment with special communication environment, users need set some environment variables. @@ -152,7 +152,7 @@ export MS_ENABLE_LCCL=off # current not support LCCL communication mode in SGLan ``` -#### Some dependencies of protobuf +### Some dependencies of protobuf In case of some environment with special protobuf version, users need set some environment variables to avoid binary version mismatch. diff --git a/docs/docs/hardware-platforms/ascend-npus/optimization/ring_sp_performance.mdx b/docs/docs/hardware-platforms/ascend-npus/optimization/ring_sp_performance.mdx index 4e1337bad..3a693c644 100644 --- a/docs/docs/hardware-platforms/ascend-npus/optimization/ring_sp_performance.mdx +++ b/docs/docs/hardware-platforms/ascend-npus/optimization/ring_sp_performance.mdx @@ -1,7 +1,7 @@ --- title: "Ring-SP Performance (Wan2.1-T2V-1.3B)" metatags: - description: "This page reports Ring-SP performance on Ascend NPU with torchnpu==2.10.0." + description: "This page reports Ring-SP performance on Ascend NPU with torch_npu==2.10.0." --- This page reports Ring-SP performance on Ascend NPU with `torch_npu==2.10.0`. diff --git a/docs/docs/supported-models/mindspore_models.mdx b/docs/docs/supported-models/mindspore_models.mdx index f47dc20dd..3e5115fc8 100644 --- a/docs/docs/supported-models/mindspore_models.mdx +++ b/docs/docs/supported-models/mindspore_models.mdx @@ -37,7 +37,7 @@ Current SGLang-MindSpore supports Qwen3 and DeepSeek V3/R1 models. This doc uses Use the following script for offline inference: -```python Offline Infer +```python Offline Inference import sglang as sgl # Initialize the engine with MindSpore backend