guqiong96/Lsglang

sglang-diffusion-performance

Use when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget.

Langue du texte source : anglais

add-jit-kernel

Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang.kernels JIT infrastructure and public operator groups

Langue du texte source : anglais

add-sgl-kernel

Step-by-step tutorial for adding a heavyweight AOT CUDA/C++ kernel to sgl-kernel (including tests & benchmarks)

Langue du texte source : anglais

kernel-organization

Apply the SGLang kernels RFC when adding, moving, splitting, or reviewing kernel APIs, registry metadata, kernel tests, benchmarks, and model-specific implementations. Use with add-jit-kernel, add-sgl-kernel, and write-sglang-test for placement and migration…

Langue du texte source : anglais

write-sglang-test

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,…

Langue du texte source : anglais

cookbook-review-pr

Review a pull request against the SGLang Cookbook (docs/, Mintlify) contribution checklist — the config-driven format (per-model config + benchmarks JSX consumed by the shared _deployment.jsx / _playground.jsx engines). Run with /cookbook-review-pr <PR…

Langue du texte source : anglais

generate-profile

Generate an e2e profiling trace of an SGLang server run. Launches a server, validates accuracy, captures a Chrome-compatible trace, and returns the profile path.

Langue du texte source : anglais

llm-torch-profiler-analysis

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…

Langue du texte source : anglais

ci-workflow-guide

Guide to SGLang CI workflow orchestration — stage ordering, fail-fast, 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…

Langue du texte source : anglais

cookbook-add-model

Add a new model to the SGLang Cookbook (docs/, Mintlify), config-driven format — instantiate the model-agnostic template into a per-model config (+ benchmarks) JSX under src/snippets/configs/, an MDX page, the docs.json nav entry, NEW-tag hygiene, and the…

Langue du texte source : anglais

clean-startup-log

Audit SGLang startup logs, save evidence, and propose cleanup for user review. With no arguments, run Qwen3-8B at TP1 and TP2 plus gpt-oss-20b at TP1.

Langue du texte source : anglais

sglang-runtime-context

How SGLang's runtime configuration and process-global state are organized (RuntimeContext tiers, publish + namespace config bags, the pristine ServerArgs seed, override entry points, resource/stream/buffer leases, per-forward flags), the CI guardrails that…

Langue du texte source : anglais

sglang-diffusion-benchmark-profile

Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.

Langue du texte source : anglais

cookbook-migrate-model

Migrate a legacy-template SGLang cookbook page (monolithic per-model generator under docs/src/snippets/autoregressive/) onto the config-driven template (shared _deployment.jsx / _playground.jsx engines + per-model config). Use when asked to migrate, convert,…

Langue du texte source : anglais

sglang-diffusion-add-model

Use when adding a new diffusion model or Diffusers pipeline to SGLang.

Langue du texte source : anglais