「sglang」の検索結果

Code style for SGLang large classes `Scheduler`, `TokenizerManager`, and `ModelRunner`: frozen-code conventions and `__init__` orchestration style. Use when modifying any of these three classes or reviewing changes to them.

日本語の概要は準備中です。原文の説明を表示しています。

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.

日本語の概要は準備中です。原文の説明を表示しています。

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.

日本語の概要は準備中です。原文の説明を表示しています。

Requirements for the SGLang scripted runtime, chiefly when to add (vs not add) a harness API. Use for anything related to the scripted runtime.

日本語の概要は準備中です。原文の説明を表示しています。

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.

日本語の概要は準備中です。原文の説明を表示しています。

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

日本語の概要は準備中です。原文の説明を表示しています。

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

日本語の概要は準備中です。原文の説明を表示しています。

Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM. Use for provider attachment, endpoint policy, credential substitution, topology, and migration from the removed managed inference endpoint. Trigger keywords - debug inference, managed inference endpoint, local inference, ollama, lm studio, vllm, sglang, trtllm, NIM, inference failing, model server unreachable, credential_endpoint_mismatch, host.openshell.internal.

日本語の概要は準備中です。原文の説明を表示しています。

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

日本語の概要は準備中です。原文の説明を表示しています。

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

日本語の概要は準備中です。原文の説明を表示しています。

Use when you need to CAPTURE / PRODUCE XProf (jax.profiler) profiling artifacts from sgl-jax (SGLang on JAX/TPU) for later performance analysis: driving a live server (/start_profile, stage-separated prefill/decode), offline bench_one_batch --profile, or kernel microbench. This skill produces the trace files; it does not analyze them.

日本語の概要は準備中です。原文の説明を表示しています。

Fornece orientação para pós-treinamento de LLM com RL usando slime, um framework Megatron+SGLang. Use ao treinar modelos GLM, implementar fluxos de trabalho personalizados de geração de dados, ou precisar de integração estreita com Megatron-LM para escalabilidade em RL.

日本語の概要は準備中です。原文の説明を表示しています。

Geração estruturada rápida e serving para LLMs com RadixAttention para cache de prefixos. Use para saídas JSON/regex, decodificação restrita, workflows com agentes que fazem chamadas de ferramentas, ou quando você precisa de 5× mais rápido que vLLM com compartilhamento de prefixos. Alimenta 300.000+ GPUs na xAI, AMD, NVIDIA e LinkedIn.

日本語の概要は準備中です。原文の説明を表示しています。

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

日本語の概要は準備中です。原文の説明を表示しています。

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

日本語の概要は準備中です。原文の説明を表示しています。

RL post-training for LLMs with Megatron and SGLang.

日本語の概要は準備中です。原文の説明を表示しています。

Make mechanical refactoring (file splits, function moves, module extractions, renames) machine-checkable instead of eyeballed. Reproduce a relocation commit byte-for-byte from faithful primitives, and split an extraction into a verifiable prepare + move + postpare. Use when doing or reviewing such changes.

日本語の概要は準備中です。原文の説明を表示しています。

Compute the optimal --mamba-full-memory-ratio (or --max-mamba-cache-size pin) for a hybrid attention + linear-attention (Mamba / GDN / KDA) model's two serving memory pools, from the workload and serving config. Use when a user asks what ratio to set, why concurrency is clamped, or how to size the state vs KV pools for a hybrid model.

日本語の概要は準備中です。原文の説明を表示しています。

Audit the existing test tree and CI configuration for improvements, using a catalog of patterns previously applied in this repo. Use when asked to audit tests or CI, shrink CI time or cost, find redundant or misplaced tests, clean up a test group, or review whether a CI change follows established practice.

日本語の概要は準備中です。原文の説明を表示しています。

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

日本語の概要は準備中です。原文の説明を表示しています。

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

日本語の概要は準備中です。原文の説明を表示しています。

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

日本語の概要は準備中です。原文の説明を表示しています。

Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.

日本語の概要は準備中です。原文の説明を表示しています。

Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin.

日本語の概要は準備中です。原文の説明を表示しています。