## What this PR does / why we need it? Fixes several documentation issues in the msprobe debugging guide as reported in #6065: 1. **Remove unnecessary `cat` heredoc wrapper**: The example configuration section used a `cat <<'JSON'` bash wrapper around the JSON config. Simplified to a plain JSON code block. 2. **Fix duplicate chapter numbering**: Two sections were both numbered '2'. Renumbered sections sequentially (0-6). 3. **Fix msprobe command**: Changed `msprobe graph_visualize` to `msprobe -f pytorch graph` in section 5.2 Visualization. 4. **Remove backward-related content**: Since vllm is inference-only (no training), removed all backward pass references including backward tensor examples, parameter gradient examples, and backward descriptions from dump.json explanations. ## Does this PR introduce _any_ user-facing change? Documentation improvement only. No code changes. ## How was this patch tested? Manual review of the markdown file to verify all 4 issues from #6065 are addressed. Closes #6065 - vLLM version: v0.16.0 - vLLM main: https://github.com/vllm-project/vllm/commit/15d76f74e2fdb12a95ea00f0ca283acf6219a2b7 Signed-off-by: NJX-njx <3771829673@qq.com>
vLLM Ascend Plugin documents
Live doc: https://docs.vllm.ai/projects/ascend
Build the docs
# Install dependencies.
pip install -r requirements-docs.txt
# Build the docs.
make clean
make html
# Build the docs with translation
make intl
# Open the docs with your browser
python -m http.server -d _build/html/
Launch your browser and open:
- English version: http://localhost:8000
- Chinese version: http://localhost:8000/zh_CN