From 624725cb5ee0be853c0250b4524f19d455f0017b Mon Sep 17 00:00:00 2001 From: Tiance Wang Date: Thu, 11 Dec 2025 15:03:50 +0800 Subject: [PATCH] Move and update MindSpore docs, make it appear on the online documentation (#14861) Co-authored-by: wangtiance Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> --- docs/index.rst | 1 + .../mindspore_models.md | 19 +++---------------- 2 files changed, 4 insertions(+), 16 deletions(-) rename docs/{references => supported_models}/mindspore_models.md (88%) diff --git a/docs/index.rst b/docs/index.rst index 0dd968352..5766fae22 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -67,6 +67,7 @@ Its core features include: supported_models/support_new_models.md supported_models/transformers_fallback.md supported_models/modelscope.md + supported_models/mindspore_models.md .. toctree:: :maxdepth: 1 diff --git a/docs/references/mindspore_models.md b/docs/supported_models/mindspore_models.md similarity index 88% rename from docs/references/mindspore_models.md rename to docs/supported_models/mindspore_models.md index 8ab5b81ce..0f8fc342b 100644 --- a/docs/references/mindspore_models.md +++ b/docs/supported_models/mindspore_models.md @@ -19,27 +19,14 @@ Currently, the following models are supported: ## Installation -> **Note**: Currently, MindSpore models are provided by an independent package `sgl-mindspore`, which needs to be installed separately. +> **Note**: Currently, MindSpore models are provided by an independent package `sgl-mindspore`. Support for MindSpore is built upon current SGLang support for Ascend NPU platform. Please first [install SGLang for Ascend NPU](../platforms/ascend_npu.md) and then install `sgl-mindspore`: ```shell -git clone https://github.com/chz34/sgl-mindspore.git +git clone https://github.com/mindspore-lab/sgl-mindspore.git cd sgl-mindspore pip install -e . ``` -You will need to install the following packages. - -```shell -pip install "mindspore==2.7.1" -pip install "torch==2.8" -pip install "torch_npu==2.8" -pip install triton_ascend -``` - -```shell -cp python/pyproject_other.toml python/pyproject.toml -pip install -e "python[all_npu]" -``` ## Run Model @@ -69,7 +56,7 @@ prompts = [ "The future of AI is" ] -sampling_params = {"temperature": 0.01, "top_p": 0.9} +sampling_params = {"temperature": 0, "top_p": 0.9} outputs = llm.generate(prompts, sampling_params) for prompt, output in zip(prompts, outputs):