メニュー
`__init__` style for SGLang `Scheduler`, `TokenizerManager`, and `ModelRunner`. Use when modifying the `__init__` of any of these three classes, or reviewing changes that add new construction logic to them.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang's jit_kernel module
Guide to SGLang CI workflow orchestration — stage ordering, fast-fail, gating, partitioning, execution modes, and debugging CI failures. Use when modifying CI workflows, adding stages, debugging CI pipeline issues, or understanding how tests are dispatched and gated across stages.
Guide for writing SGLang CI/UT tests. Covers CustomTestCase, CI registration, server fixtures, model selection, mock testing, and test placement. Always read test/README.md for the full CI layout, how to run tests, and extra tips. Use when creating new tests, adding CI test cases, writing unit tests, or when the user asks to add tests for SGLang features.
Unified LLM torch-profiler triage skill for `sglang`, `vllm`, `TensorRT-LLM`, and `TokenSpeed`. Use it to inspect an existing `trace.json(.gz)` or profile directory, or to drive live profiling against a running server when supported and return one three-table report with kernel, overlap-opportunity, and fuse-pattern tables.
Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.
Use when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget.
| name | large-class-init-style |
| description | `__init__` style for SGLang `Scheduler`, `TokenizerManager`, and `ModelRunner`. Use when modifying the `__init__` of any of these three classes, or reviewing changes that add new construction logic to them. |
__init__ Style for Scheduler / TokenizerManager / ModelRunnerApply when modifying the __init__ of:
Scheduler — python/sglang/srt/managers/scheduler.pyTokenizerManager — python/sglang/srt/managers/tokenizer_manager.pyModelRunner — python/sglang/srt/model_executor/model_runner.py__init__, which rots against upstream.init_* helpers lets them override exactly what they need.TokenizerManager.__init__ in python/sglang/srt/managers/tokenizer_manager.py.__init__ is an orchestrator. Sequence of self.init_*(...) calls + minimal glue. No non-trivial construction inlined.init_* = one concern a subclass might swap. Don't lump.init_<thing> (snake_case, names the component). Conditional construction → maybe_init_<thing>, gate inside the helper.self.* set by earlier helpers. Ordering lives in __init__. Shared intermediates → pass as args, not via self.*.init_<thing>, not another inline block. One-line self.foo = server_args.foo is fine; structured logic is not.init_* signatures. Breaking changes → call out in PR.Only the three classes listed above. Not other manager-style classes, not small dataclass/utility constructors.