SGLang HiCache (hierarchical KV cache) — three-tier prefix cache: GPU HBM (L1) → pinned host DRAM (L2) → distributed L3 (Mooncake / 3FS / NIXL / AIBrix / EIC / SiMM / file / LMCache). Covers --enable-hierarchical-cache, all --hicache- flags, write policies, pagefirst layouts, prefetch policy (besteffort / waitcomplete / timeout), per-rank sizing, MHA / MLA / DSA / Mamba / SWA support matrix (hybrid attention still landing in v0.5.11), runtime attach/detach HTTP admin, and auto-rewrite startup log lines that silently substitute layout × IO × storage combinations.
EnglishEnd-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM serving performance by searching each framework's best deployment command, benchmarking them fairly, profiling SGLang if it is slower, identifying kernel/overlap/fusion bottlenecks, patching SGLang code, and revalidating with real model runs.
English
AGENT SKILLS ATLASIncludes Sglang Hicache, Sglang Sota Performance, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Sglang
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, o
Sglang Hicache
SGLang HiCache (hierarchical KV cache) — three-tier prefix cache: GPU HBM (L1) → pinned host DRAM (L2) → distributed L3 (Mooncake / 3FS / NIXL / AIBrix / EIC / SiMM / file / LMCache). Covers --enable-hierarchical-cache, all --hicache- flags, write policies, pagefirst layouts, prefetch policy (besteffort / waitcomplete / timeout), per-rank sizing, MHA / MLA / DSA / Mamba / SWA support matrix (hybrid attention still landing in v0.5.11), runtime attach/detach HTTP admin, and auto-rewrite startup log lines that silently substitute layout × IO × storage combinations.
Sglang Sota Performance
End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM serving performance by searching each framework's best deployment command, benchmarking them fairly, profiling SGLang if it is slower, identifying kernel/overlap/fusion bottlenecks, patching SGLang code, and revalidating with real model runs.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Sglang skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported licenses for the skills shown: MIT, Apache-2.0. The author’s terms apply.