sgl-project/sglang

121 other commands the scanner could not classify

Commands from CI steps and task runners that look like checks but match no known tool. Some are checks, some are not.

• PR Test AMD ROCm10 + ROCm7.2.4 + ROCm7.2.0 Gate
• assert spec is not None and spec.loader is not None
• bash -c 'cd rust
• bash -c 'cd sgl-router
• bash -c 'rustup component add --toolchain nightly rustfmt >/dev/null
• bash ../scripts/ci/npu/precise-test/run_tests_with_coverage.sh $(cat /tmp/selected_tests.txt)
• bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-test-time-deps
• bash scripts/ci/npu/precise-test/run_tests_with_coverage.sh $(cat /tmp/selected_tests.txt)
• bash scripts/ci/ppu/build_and_test.sh build
• bash scripts/ci/ppu/run_test.sh
• bash scripts/release/commit_and_pr.sh docs install $EXPR $BRANCH_NAME
• cannot verify whether ${FULL_SHA} is merged."
• cargo doc --open
• check its ACL"
• check-all-jobs
• check-changes
• checks skipped."
• coverage combine --rcfile=/tmp/report-rc --keep $(find ${COV_ROOT} -name coverage.* -type f)
• coverage html --rcfile=/tmp/report-rc --directory=${REPORT_DIR}
• coverage html --rcfile=/tmp/report-rc --include=*/sglang/srt/hardware_backend/npu/* --directory=${REPORT_DIR}-npu
• coverage report --rcfile=/tmp/report-rc
• coverage report --rcfile=/tmp/report-rc --include='*/sglang/srt/hardware_backend/npu/*'
• data = CoverageData(basename=/tmp/.coverage-npu)
• done <<< ${ONLY_TESTS}
• du -h test_case_map.json
• from coverage import CoverageData
• inspection = load(
• inspection_path = production_path.with_name(
• log -1 --format=%s $FULL_SHA)
• mem_cache_inspection + suffix
• mint broken-links --check-anchors --check-redirects
• mint broken-links --check-anchors --check-redirects'
• module = importlib.util.module_from_spec(spec)
• no PPU tests were requested.'
• node docs/scripts/check_cookbook_configs.mjs
• pr-test-amd-finish
• pre-commit hook check-shebang-scripts-are-executable
• pre-commit hook check-symlinks
• pre-commit hook clang-format
• pre-commit hook destroyed-symlinks

full scan as JSON

• eliminate code duplicationActively identify and eliminate code duplication by extracting common patterns into reusable components. When you notice repeated code bl...

  sgl-project/sglang Code Style Python llm-infra 2025-08-21

  copy raw open
• Improve code organizationPrioritize clean code structure and readability in AI/ML codebases by avoiding inline conditionals, using descriptive expressions, and ma...

  sgl-project/sglang AI Python llm-infra 2025-08-25

  copy raw open
• Eliminate redundant operationsAvoid duplicate function calls, repeated tensor operations, and redundant computations that can significantly impact performance. Impleme...

  sgl-project/sglang Performance Optimization Python llm-infra 2025-08-22

  copy raw open
• Use descriptive namesChoose variable, function, and parameter names that accurately reflect their content, type, and purpose. Avoid misleading names that don'...

  sgl-project/sglang Naming Conventions Python llm-infra 2025-08-13

  copy raw open
• Verify algorithmic correctnessEnsure algorithmic implementations are correct before applying optimizations or complex conditional logic. This is especially critical fo...

  sgl-project/sglang Algorithms Python llm-infra 2025-08-21

  copy raw open
• Use Optional types safelyAlways use proper nullable type annotations and safe access patterns to prevent runtime errors from null/undefined values. Use `Optional[...

  sgl-project/sglang Null Handling Python llm-infra 2025-08-20

  copy raw open
• Optimize cache performancePrioritize cache performance by leveraging proven optimization techniques and avoiding performance anti-patterns. Use standard caching de...

  sgl-project/sglang Caching Python llm-infra 2025-08-19

  copy raw open
• Prevent race conditionsEnsure atomic operations and proper synchronization when multiple threads or processes access shared state. Race conditions occur when th...

  sgl-project/sglang Concurrency Python llm-infra 2025-08-11

  copy raw open
• Environment variable best practicesAvoid reading environment variables directly in performance-critical code paths, especially during model forward passes or hot loops. Ins...

  sgl-project/sglang Configurations Python llm-infra 2025-08-19

  copy raw open
• Explicit API parametersAPI functions should use explicit parameters rather than passing large opaque objects. When a function needs specific data from a complex...

  sgl-project/sglang API Python llm-infra 2025-08-13

  copy raw open
• optimize tensor operationsWhen working with PyTorch tensors, prioritize operations that avoid unnecessary memory allocations and copies to improve performance. Cho...

  sgl-project/sglang Pytorch Python llm-infra 2025-08-13

  copy raw open
• Document AI limitationsWhen implementing AI model support or hardware backends, clearly document known limitations, compatibility constraints, and version requi...

  sgl-project/sglang AI Markdown llm-infra 2025-08-10

  copy raw open
• Avoid broad exception catchingAvoid using overly broad exception handling like `except Exception` as it can mask specific errors and make debugging difficult. Instead,...

  sgl-project/sglang Error Handling Python llm-infra 2025-08-19

  copy raw open
• consolidate duplicated logicWhen you identify duplicated code patterns across different branches or functions, consolidate the shared logic into a unified implementa...

  sgl-project/sglang Code Style CUDA llm-infra 2025-08-10

  copy raw open
• AI model documentation consistencyEnsure consistent parameter names and configuration instructions across AI model documentation. Inconsistent documentation about model pa...

  sgl-project/sglang AI Other llm-infra 2025-07-27

  copy raw open
• AI dependency justificationWhen modifying AI library dependencies, always provide clear justification for version choices, especially when using non-standard source...

  sgl-project/sglang AI Toml llm-infra 2025-07-24

  copy raw open
• CUDA compatibility verificationWhen modifying CUDA versions or GPU architecture configurations in AI/ML projects, verify compatibility across three critical dimensions:...

  sgl-project/sglang AI Dockerfile llm-infra 2025-07-18

  copy raw open